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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change of state or condition

    oai_token-act-pair · gpt-3.5-turbo

    words related to abandonment or a lack of presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.71
    ALLY
    -0.71
    andan
    -0.65
     Cosponsors
    -0.65
    alian
    -0.64
    wana
    -0.63
    alez
    -0.62
    buster
    -0.62
     Refer
    -0.61
    idium
    -0.59
    POSITIVE LOGITS
     behind
    1.12
     undone
    0.99
     scars
    0.97
     intact
    0.94
    overs
    0.93
     unanswered
    0.92
     gaping
    0.92
     unfinished
    0.89
     untold
    0.88
     footprints
    0.85
    Act Density 0.048%

    No Known Activations