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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation patterns

    oai_token-act-pair · gpt-3.5-turbo

    structured data or code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     footing
    -0.55
    .""
    -0.55
    radical
    -0.54
    being
    -0.52
    rad
    -0.51
    older
    -0.51
    cuts
    -0.50
    nor
    -0.50
    cerning
    -0.50
     compromise
    -0.49
    POSITIVE LOGITS
    ↵
    0.77
     Franch
    0.59
     STORY
    0.55
    iona
    0.54
    ????????
    0.53
     Lens
    0.53
     Adinida
    0.52
     Phi
    0.52
    rium
    0.51
    ENG
    0.50
    Act Density 0.540%

    No Known Activations