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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and actions related to physical or social discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingers
    -0.17
    reator
    -0.16
    ADOS
    -0.15
    inery
    -0.14
    stal
    -0.14
    ãģ¯ãģļ
    -0.14
    intent
    -0.14
    baz
    -0.14
    _FLUSH
    -0.14
    chez
    -0.14
    POSITIVE LOGITS
     harder
    0.18
     uncont
    0.18
     prof
    0.17
    -fit
    0.17
     viol
    0.17
     fit
    0.17
     recalling
    0.16
    -hard
    0.16
    Visible
    0.15
     inward
    0.15
    Act Density 0.158%

    No Known Activations