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

    Neuronpedia

    INDEX
    Explanations

    sentences containing comparisons or evaluations of likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing perceptions or judgments about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isner
    -0.73
     srfAttach
    -0.67
    ogh
    -0.65
    pour
    -0.64
    ioch
    -0.64
    redo
    -0.64
    chance
    -0.63
    hurst
    -0.62
    addin
    -0.62
    orously
    -0.60
    POSITIVE LOGITS
     blush
    0.78
     innocuous
    0.76
     superf
    0.74
     daunting
    0.69
     confusing
    0.69
     confused
    0.68
     differently
    0.68
     acron
    0.67
     slightly
    0.66
    INGS
    0.66
    Act Density 0.084%

    No Known Activations