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

    Neuronpedia

    INDEX
    Explanations

    actions related to animals and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.71
    isSpecialOrderable
    -0.64
    displayText
    -0.62
    é¾įåĸļ士
    -0.61
    ILS
    -0.60
    ITION
    -0.59
     APPLIC
    -0.57
    èĢħ
    -0.57
    FIN
    -0.57
    ç«
    -0.56
    POSITIVE LOGITS
     themselves
    0.83
     their
    0.71
     extinct
    0.69
     THEIR
    0.69
     Their
    0.69
     wives
    0.63
    selves
    0.62
    their
    0.62
     helmets
    0.62
     uniforms
    0.57
    Act Density 0.420%

    No Known Activations