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

    Neuronpedia

    INDEX
    Explanations

    words related to successful or unsuccessful outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "work" or its variants, indicating discussions about workability or effectiveness of strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anamo
    -0.85
    antha
    -0.81
    ailable
    -0.74
    sbm
    -0.66
    76561
    -0.64
    pora
    -0.64
    ople
    -0.63
    xual
    -0.63
     Browse
    -0.62
    gart
    -0.62
    POSITIVE LOGITS
     wonders
    1.32
     miracles
    1.18
    heet
    1.09
     harder
    0.96
     overtime
    0.93
     tirelessly
    0.92
     flaw
    0.92
    bench
    0.92
     brilliantly
    0.91
     against
    0.91
    Act Density 0.051%

    No Known Activations