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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    躇
    -0.60
     Exacts
    -0.57
    RTSC
    -0.54
    ScopeManager
    -0.54
    gnore
    -0.53
    Gön
    -0.53
    Географи
    -0.52
    重
    -0.51
     correctes
    -0.50
    Климат
    -0.50
    POSITIVE LOGITS
     widest
    0.83
     broadly
    0.81
     broadest
    0.78
     broad
    0.77
     breiten
    0.76
     wider
    0.76
     wide
    0.74
     широ
    0.69
     broader
    0.69
    wider
    0.68
    Act Density 0.165%

    No Known Activations