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

    Neuronpedia

    INDEX
    Explanations

    **unique characteristics or actions performed by individuals.**

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the uniqueness or absence of experience among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.71
    ahime
    -0.70
     unden
    -0.68
     Locations
    -0.66
    ß
    -0.64
    ãĥ¯
    -0.63
    catentry
    -0.63
    ivities
    -0.63
    ortment
    -0.63
     rall
    -0.63
    POSITIVE LOGITS
    else
    0.84
     knows
    0.82
    kn
    0.78
     bothered
    0.77
    who
    0.71
    afia
    0.70
    lihood
    0.70
     whom
    0.69
     fault
    0.67
     bothering
    0.65
    Act Density 0.227%

    No Known Activations