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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing high certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    assurances or guarantees about outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĢħ
    -0.74
    ublic
    -0.71
     contrace
    -0.71
    GROUP
    -0.63
    ystem
    -0.62
    OPLE
    -0.61
    vernment
    -0.60
    ynchron
    -0.60
     concurrently
    -0.57
     largeDownload
    -0.57
    POSITIVE LOGITS
    footed
    1.37
    fire
    1.30
    ty
    1.13
    ties
    0.97
    faced
    0.90
    ndra
    0.88
    fires
    0.88
    fold
    0.82
     Gamble
    0.81
    fired
    0.80
    Act Density 0.029%

    No Known Activations