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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Added
    -0.68
    whe
    -0.67
    EMENT
    -0.64
    esses
    -0.64
    hess
    -0.61
    escription
    -0.60
    ourse
    -0.60
    erity
    -0.60
     nonetheless
    -0.60
    azz
    -0.59
    POSITIVE LOGITS
    lihood
    0.97
     ours
    0.97
    oxide
    0.78
     theirs
    0.74
    ptions
    0.69
    angular
    0.68
    lier
    0.66
    invoke
    0.65
    agate
    0.64
     chronological
    0.64
    Act Density 0.069%

    No Known Activations