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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectation or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations or predictions about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.71
    Interstitial
    -0.68
     Highway
    -0.64
    backer
    -0.62
    aura
    -0.61
    reen
    -0.61
    toggle
    -0.60
    bum
    -0.59
    conservancy
    -0.58
    neck
    -0.58
    POSITIVE LOGITS
    antly
    0.76
    ĩ
    0.73
    olate
    0.72
    orate
    0.71
    ħ
    0.71
    WARD
    0.70
    ı
    0.70
    anamo
    0.69
    ORY
    0.68
    ĭ
    0.67
    Act Density 0.027%

    No Known Activations