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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data collection and analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate objectives or goals related to actions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hemor
    -0.64
    Ń·
    -0.60
     è£ıç
    -0.58
     trenches
    -0.56
    ãĥIJ
    -0.56
     pse
    -0.56
     squares
    -0.56
    ortment
    -0.54
     towels
    -0.54
     tending
    -0.53
    POSITIVE LOGITS
    oca
    0.68
    INESS
    0.65
    uce
    0.63
    ocation
    0.62
    FK
    0.62
    ocard
    0.61
    igmat
    0.57
    :]
    0.57
    umar
    0.56
    uate
    0.56
    Act Density 0.328%

    No Known Activations