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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -1.15
     Савезне
    -0.94
    tvguidetime
    -0.92
    Personendaten
    -0.91
     Theſe
    -0.89
    RUnlock
    -0.86
    зулта
    -0.86
     ModelExpression
    -0.86
     opérateur
    -0.86
     myſelf
    -0.83
    POSITIVE LOGITS
    To
    1.23
    to
    1.12
     To
    1.04
    TO
    0.92
     TO
    0.74
    And
    0.59
     То
    0.58
    tos
    0.57
    То
    0.56
    on
    0.56
    Act Density 0.267%

    No Known Activations