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

    Neuronpedia

    INDEX
    Explanations

    numeric quantities and descriptions of containment or possession

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical quantities and individuals involved in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fits
    -0.74
    reads
    -0.71
    Reply
    -0.65
    bara
    -0.65
    orum
    -0.64
     Madness
    -0.62
     Sabha
    -0.62
     Mahjong
    -0.61
     Practices
    -0.60
    orian
    -0.59
    POSITIVE LOGITS
     ones
    0.71
    enegger
    0.66
     aforementioned
    0.66
     tradem
    0.63
    illions
    0.61
    rowing
    0.60
    aband
    0.60
    ãĤ¶
    0.59
    otally
    0.59
    ò
    0.58
    Act Density 0.269%

    No Known Activations