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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative experiences or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amusement
    -0.76
     characteristic
    -0.73
     convenience
    -0.71
     absence
    -0.71
     lifetime
    -0.69
     Tsukuyomi
    -0.67
     Sunshine
    -0.66
     constituent
    -0.65
     Identification
    -0.64
     proceeding
    -0.64
    POSITIVE LOGITS
    raise
    1.15
    activate
    1.14
    handedly
    1.14
    heartedly
    1.11
    apply
    1.10
    create
    1.09
    react
    1.06
    fill
    1.03
    align
    1.03
    ply
    1.02
    Act Density 0.042%

    No Known Activations