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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "for" and related prepositional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĪ
    -0.16
    glob
    -0.16
    olib
    -0.15
     thủy
    -0.15
    .pa
    -0.14
    \OptionsResolver
    -0.14
    IAS
    -0.14
    пÑĤом
    -0.14
    ÑĤами
    -0.14
     Glover
    -0.14
    POSITIVE LOGITS
    quer
    0.18
    asar
    0.17
    zer
    0.17
     fat
    0.16
    ÃĴ
    0.15
    omo
    0.15
     bar
    0.14
    emic
    0.14
     Fat
    0.14
    unan
    0.14
    Act Density 0.001%

    No Known Activations