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

    Neuronpedia

    INDEX
    Explanations

    suggestions or invitations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or interest in actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    semble
    -0.79
    eding
    -0.71
    VERTISEMENT
    -0.67
    bard
    -0.65
    à¼
    -0.65
    workers
    -0.64
    ammy
    -0.64
    cript
    -0.63
    ccording
    -0.63
    gren
    -0.63
    POSITIVE LOGITS
    reprene
    0.84
    urities
    0.81
    htar
    0.65
     warr
    0.64
    atem
    0.64
    AGES
    0.64
    atis
    0.63
    iasis
    0.63
    ãĤ¦ãĤ¹
    0.63
    edIn
    0.61
    Act Density 0.062%

    No Known Activations