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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to enabling or allowing something to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the capacity or power to perform actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Warcraft
    -0.76
    boy
    -0.73
    bane
    -0.72
    apest
    -0.71
     Nose
    -0.71
    den
    -0.70
     Rite
    -0.67
     Soda
    -0.65
     Kore
    -0.63
    ynski
    -0.63
    POSITIVE LOGITS
    auga
    0.87
    iences
    0.82
    untarily
    0.80
    berra
    0.77
     enables
    0.77
     interoper
    0.77
    ibaba
    0.76
    ments
    0.75
    Reviewer
    0.75
    jriwal
    0.74
    Act Density 0.027%

    No Known Activations