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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions related to engagement and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    égor
    -0.16
    omor
    -0.16
    reator
    -0.15
    itre
    -0.15
    ilet
    -0.15
    yx
    -0.14
    many
    -0.14
    atan
    -0.14
    .vertx
    -0.14
    à¸Ńà¸ĩ
    -0.14
    POSITIVE LOGITS
     away
    0.38
     Away
    0.30
    Away
    0.28
    -away
    0.28
    away
    0.25
     harder
    0.16
     till
    0.16
    lk
    0.15
     sobie
    0.15
     mad
    0.15
    Act Density 0.162%

    No Known Activations