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

    Neuronpedia

    INDEX
    Explanations

    explanations or statements about expectations or predictions

    oai_token-act-pair · gpt-3.5-turbo

    the word "expect" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tex
    -0.70
    pmwiki
    -0.68
    backer
    -0.64
    neck
    -0.62
    anski
    -0.62
    issance
    -0.60
    reen
    -0.60
    aura
    -0.59
    Interstitial
    -0.59
    add
    -0.58
    POSITIVE LOGITS
    antly
    0.81
    iour
    0.72
     bruises
    0.71
    WARD
    0.71
    olate
    0.70
    ı
    0.69
    ĩ
    0.69
    ħ
    0.67
    lessly
    0.67
    anamo
    0.67
    Act Density 0.030%

    No Known Activations