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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis or data interpretation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]<<"
    -0.59
    لكتر
    -0.58
    valently
    -0.58
    ginous
    -0.56
    StreetMap
    -0.56
     profane
    -0.55
     repatri
    -0.54
    InitVars
    -0.53
    mitglied
    -0.52
     aspir
    -0.52
    POSITIVE LOGITS
    tainment
    0.78
    ishment
    0.78
    iction
    0.74
    lization
    0.69
    uation
    0.68
    ulation
    0.67
    enumii
    0.67
    iration
    0.67
    ination
    0.66
    pation
    0.66
    Act Density 0.883%

    No Known Activations