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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sequence of actions or steps

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    marine
    -0.67
    reens
    -0.59
    minent
    -0.58
     Sleeping
    -0.55
     Berks
    -0.54
     Ve
    -0.54
     outweigh
    -0.53
     drowned
    -0.52
     ankles
    -0.51
    onite
    -0.51
    POSITIVE LOGITS
     meantime
    0.77
     refres
    0.74
    awaru
    0.68
    ety
    0.65
     disclaimer
    0.65
     disclaim
    0.64
    ratulations
    0.64
    forming
    0.63
    antha
    0.62
    isites
    0.61
    Act Density 0.159%

    No Known Activations