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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verb conjugations

    oai_token-act-pair · gpt-3.5-turbo

    words related to choices and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jou
    -0.68
     CSI
    -0.67
    axis
    -0.66
     Cologne
    -0.65
     Jasper
    -0.65
    atem
    -0.65
     Kem
    -0.64
     Helic
    -0.64
     Seahawks
    -0.63
     JA
    -0.63
    POSITIVE LOGITS
    not
    1.16
     not
    1.10
    no
    0.98
     nonex
    0.98
    nt
    0.97
    lessness
    0.96
    NOT
    0.94
     NOT
    0.94
    Not
    0.91
    never
    0.90
    Act Density 0.179%

    No Known Activations