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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a desire to communicate or engage with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exact
    -0.18
    ioni
    -0.15
    dorf
    -0.15
    esar
    -0.15
    Exact
    -0.14
    uja
    -0.14
     Exact
    -0.14
    arto
    -0.14
    ua
    -0.14
     mys
    -0.14
    POSITIVE LOGITS
    REDENTIAL
    0.17
     Marsh
    0.15
    âĢĮØ¢
    0.15
    \model
    0.14
    adoo
    0.14
    igr
    0.14
    деÑĢж
    0.14
     Marshal
    0.14
    Marsh
    0.14
    APPER
    0.14
    Act Density 0.009%

    No Known Activations