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

    Neuronpedia

    INDEX
    Explanations

    news agencies and press publications

    oai_token-act-pair · gpt-3.5-turbo

    references to the Associated Press (AP)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    changed
    -0.74
    weights
    -0.65
     chilling
    -0.63
    gaard
    -0.62
     stabil
    -0.62
    chest
    -0.61
     phyl
    -0.61
    abiding
    -0.60
     gluten
    -0.59
    wagen
    -0.58
    POSITIVE LOGITS
    TN
    1.08
    PLE
    1.07
    PLIC
    0.95
    PLA
    0.94
    PLIED
    0.91
    ocalypse
    0.90
    PE
    0.89
    oleon
    0.88
     Photo
    0.86
    rison
    0.86
    Act Density 0.015%

    No Known Activations