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

    Neuronpedia

    INDEX
    Explanations

    names or identifiers, particularly in a context of searching for information about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rhet
    -0.15
    -Language
    -0.14
    istar
    -0.14
    anonymous
    -0.14
    ktop
    -0.14
    unsch
    -0.14
     rhetoric
    -0.13
    empor
    -0.13
    aders
    -0.13
    adm
    -0.13
    POSITIVE LOGITS
     spell
    0.50
    pron
    0.44
     pron
    0.41
    spell
    0.41
     spelling
    0.41
    Spell
    0.41
     Spell
    0.41
     pronounce
    0.40
     pronounced
    0.39
     pronunciation
    0.38
    Act Density 0.171%

    No Known Activations