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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    words related to voice and vocal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stones
    -0.86
    neys
    -0.81
    ãĥĥãĥī
    -0.75
    ning
    -0.74
    ents
    -0.74
    rod
    -0.73
    port
    -0.72
    ãĤ·ãĥ£
    -0.72
    Pain
    -0.71
    opic
    -0.71
    POSITIVE LOGITS
    xual
    1.05
    zzle
    0.77
    inion
    0.75
    scill
    0.74
    REDACTED
    0.73
    mble
    0.73
    ipop
    0.72
    iland
    0.71
     redundancy
    0.69
     vo
    0.68
    Act Density 0.049%

    No Known Activations