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

    Neuronpedia

    INDEX
    Explanations

    the letter 's followed by a verb in present tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resorts
    -0.68
    glomer
    -0.65
     colonies
    -0.63
     hordes
    -0.63
     snail
    -0.62
     labou
    -0.60
     Spani
    -0.59
     mobilization
    -0.58
     runoff
    -0.58
     coh
    -0.58
    POSITIVE LOGITS
    andi
    0.86
     gonna
    0.81
    areth
    0.80
    ahime
    0.78
    %"
    0.75
    initely
    0.74
    alone
    0.72
     [+
    0.72
    leeve
    0.71
    Da
    0.70
    Act Density 0.209%

    No Known Activations