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

    Neuronpedia

    INDEX
    Explanations

    substitutes or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    references to substitutions or alternate options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worthiness
    -0.79
    Bird
    -0.77
    raq
    -0.73
    iland
    -0.69
    trust
    -0.67
    20439
    -0.66
    erers
    -0.66
    bra
    -0.66
    slaught
    -0.65
    brace
    -0.65
    POSITIVE LOGITS
    itute
    1.06
    utions
    0.98
     substitute
    0.90
     substitutes
    0.87
     substit
    0.86
     Subst
    0.82
    uting
    0.79
    itutes
    0.75
    aneous
    0.73
     substituted
    0.72
    Act Density 0.020%

    No Known Activations