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

    Neuronpedia

    INDEX
    Explanations

    numbers, ranks, and sequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating characteristics of a specific entity or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricks
    -0.66
    anyon
    -0.61
    %;
    -0.58
    midt
    -0.57
    iscons
    -0.55
    ennett
    -0.55
    antics
    -0.55
    ummies
    -0.54
    chev
    -0.54
    hov
    -0.53
    POSITIVE LOGITS
     incidentally
    0.59
    SPONSORED
    0.57
    pires
    0.55
     reside
    0.53
     Beach
    0.52
     genetically
    0.52
     resides
    0.52
    pire
    0.51
    GMT
    0.51
    nant
    0.50
    Act Density 1.159%

    No Known Activations