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

    Neuronpedia

    INDEX
    Explanations

    the verb "become"

    oai_token-act-pair · gpt-4-turbo

    phrases hinting at the future or transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "become."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inarily
    -0.72
    oning
    -0.70
    inately
    -0.68
    otropic
    -0.68
    umbo
    -0.66
    atching
    -0.66
    enger
    -0.65
     Cran
    -0.64
    erity
    -0.63
    aceous
    -0.60
    POSITIVE LOGITS
     accustomed
    0.95
     entangled
    0.88
     extinct
    0.87
    ãĤ£
    0.81
     embroiled
    0.79
    nces
    0.78
     obsolete
    0.77
     acquainted
    0.75
     withdrawn
    0.75
     disillusion
    0.74
    Act Density 0.052%

    No Known Activations