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

    Neuronpedia

    INDEX
    Explanations

    references to sequels or subsequent parts of a series

    oai_token-act-pair · gpt-3.5-turbo

    references to installments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eric
    -0.78
    gans
    -0.72
    aiman
    -0.71
    yer
    -0.70
    bara
    -0.69
    mouth
    -0.69
    ello
    -0.69
    eating
    -0.68
    acia
    -0.67
    idi
    -0.65
    POSITIVE LOGITS
     installment
    1.24
     installments
    1.08
    itial
    0.74
    ĸļ
    0.70
     dues
    0.69
     thereof
    0.69
    Charges
    0.68
    ription
    0.68
     Tactics
    0.68
     iteration
    0.67
    Act Density 0.007%

    No Known Activations