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

    Neuronpedia

    INDEX
    Explanations

    dense clusters of syllables

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ply
    -0.88
     LIN
    -0.86
     Tenth
    -0.77
     Veronica
    -0.75
     Leth
    -0.75
    LY
    -0.74
     Rud
    -0.73
    TERN
    -0.72
     Lud
    -0.71
     VID
    -0.71
    POSITIVE LOGITS
    af
    1.39
    agen
    1.38
    á
    1.33
    abo
    1.32
    aco
    1.32
    ach
    1.31
    ac
    1.31
    av
    1.30
    ak
    1.28
    ag
    1.26
    Act Density 0.262%

    No Known Activations