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

    Neuronpedia

    INDEX
    Explanations

    mentions of recent events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Recently."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imm
    -0.74
    onite
    -0.66
     Strait
    -0.66
    afort
    -0.63
    ilot
    -0.62
    orney
    -0.61
    llah
    -0.60
    anza
    -0.60
    cair
    -0.59
    igm
    -0.59
    POSITIVE LOGITS
    theless
    0.76
     Updated
    0.71
     Tonight
    0.69
     Supplement
    0.68
     Update
    0.67
     Yesterday
    0.67
    episode
    0.67
    antine
    0.66
    ynski
    0.65
    Recently
    0.64
    Act Density 0.017%

    No Known Activations