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

    Neuronpedia

    INDEX
    Explanations

    the word "envisaged" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to planning or predicting future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.70
    die
    -0.69
    Du
    -0.68
    bye
    -0.68
    wa
    -0.67
    guard
    -0.67
    hide
    -0.66
    GU
    -0.65
    bery
    -0.65
    idity
    -0.63
    POSITIVE LOGITS
     envision
    0.99
    eers
    0.95
     visions
    0.88
    ufact
    0.86
    urations
    0.82
    alist
    0.78
     envis
    0.78
     envisioned
    0.77
    enance
    0.73
    eering
    0.73
    Act Density 0.033%

    No Known Activations