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

    Neuronpedia

    INDEX
    Explanations

    instances of everyday activities and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalar
    -0.15
    amina
    -0.15
    аний
    -0.14
     shotgun
    -0.14
    anian
    -0.14
    efa
    -0.14
     Trend
    -0.14
     Kraj
    -0.14
    /features
    -0.13
    agnost
    -0.13
    POSITIVE LOGITS
     regular
    0.36
     normally
    0.36
    normally
    0.31
     usual
    0.31
    regular
    0.31
     normal
    0.30
     regularly
    0.30
     previous
    0.28
     previously
    0.27
     Normally
    0.26
    Act Density 0.206%

    No Known Activations