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

    Neuronpedia

    INDEX
    Explanations

    dialogue and expressions of emotional interactions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /ag
    -0.16
    atoi
    -0.15
    autop
    -0.15
    ANTA
    -0.15
    isor
    -0.15
    맹
    -0.14
    /apt
    -0.14
    acios
    -0.14
    éĴ®
    -0.14
    anchor
    -0.14
    POSITIVE LOGITS
     Ar
    0.93
    Ar
    0.91
     ar
    0.82
    -ar
    0.82
    _ar
    0.80
     AR
    0.79
    .Ar
    0.73
     ÐIJÑĢ
    0.71
    .ar
    0.71
     аÑĢ
    0.63
    Act Density 0.387%

    No Known Activations