Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and recommendations related to experiences or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before positive recommendations

    np_acts-logits-general · gemini-2.0-flash

    would recommend or repeat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.82
    WithMany
    -0.74
    verwijspagina
    -0.74
    ConstraintMaker
    -0.73
     invokingState
    -0.70
    ParallelGroup
    -0.70
    DockStyle
    -0.70
     Administrativna
    -0.69
     transfieras
    -0.66
    pierw
    -0.65
    POSITIVE LOGITS
     again
    0.79
     repetir
    0.65
     repeat
    0.64
     wieder
    0.64
     sicuramente
    0.58
    again
    0.57
     recommending
    0.56
     Again
    0.55
    Again
    0.55
     definitely
    0.55
    Act Density 0.055%

    No Known Activations