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

    Neuronpedia

    INDEX
    Explanations

    words related to discussing or implying something

    oai_token-act-pair · gpt-3.5-turbo

    present and past tense verbs related to suggesting, theorizing, or signaling ideas and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Buzz
    -0.65
    ograp
    -0.64
    ãĥ¼ãĥ«
    -0.63
    åĭ
    -0.61
     unequ
    -0.60
    meter
    -0.60
    rimp
    -0.59
     Splash
    -0.56
    Cop
    -0.56
    ãģĹ
    -0.56
    POSITIVE LOGITS
    LY
    0.87
    ially
    0.87
    atively
    0.84
    enance
    0.74
    erred
    0.72
    xus
    0.72
     aloud
    0.72
    own
    0.71
    ean
    0.69
    ij士
    0.69
    Act Density 0.089%

    No Known Activations