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

    Neuronpedia

    INDEX
    Explanations

    statements describing something as impressive or praiseworthy

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong positive sentiment or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    epend
    -0.86
    ©¶æ
    -0.80
    eter
    -0.78
    vere
    -0.75
    aper
    -0.75
    pai
    -0.75
    embed
    -0.74
    gging
    -0.74
    few
    -0.72
    erton
    -0.72
    POSITIVE LOGITS
     feat
    0.91
     rendition
    0.88
     feats
    0.87
     coincidence
    0.85
    NESS
    0.83
     accomplishment
    0.76
     amounts
    0.76
     achievement
    0.74
     talent
    0.74
     creations
    0.68
    Act Density 0.044%

    No Known Activations