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

    Neuronpedia

    INDEX
    Explanations

    words related to institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of research centers or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ths
    -0.73
    added
    -0.69
     Luthor
    -0.67
    soDeliveryDate
    -0.61
     retard
    -0.61
    except
    -0.60
    ods
    -0.59
     Hut
    -0.57
    eting
    -0.57
     Uz
    -0.56
    POSITIVE LOGITS
    pieces
    1.12
    piece
    0.99
    tyard
    0.87
    fold
    0.84
    lington
    0.81
     fielder
    0.79
     pamph
    0.77
    arity
    0.76
    ologies
    0.75
    eous
    0.74
    Act Density 0.035%

    No Known Activations