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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing the word "last."

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "last."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.80
    gans
    -0.80
    cil
    -0.72
    olutions
    -0.71
    eers
    -0.70
    orsi
    -0.67
    ordes
    -0.67
    keyes
    -0.66
    andise
    -0.65
    İĭ
    -0.65
    POSITIVE LOGITS
     ditch
    0.89
     gasp
    0.86
     week
    0.86
    ebin
    0.83
     Gleaming
    0.82
     month
    0.81
     minute
    0.78
    fm
    0.77
     rites
    0.76
     night
    0.75
    Act Density 0.066%

    No Known Activations