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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparison or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACA
    -0.77
    ICA
    -0.64
    chemical
    -0.63
    TC
    -0.61
    Around
    -0.60
    latest
    -0.59
    oller
    -0.59
    CCC
    -0.58
    MD
    -0.57
     seriousness
    -0.57
    POSITIVE LOGITS
    bestos
    0.92
    pects
    0.88
     regards
    0.86
    ynchron
    0.84
     evidenced
    0.81
    pired
    0.80
    ylum
    0.79
    phalt
    0.74
    ociated
    0.74
    pires
    0.73
    Act Density 0.043%

    No Known Activations