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

    Neuronpedia

    INDEX
    Explanations

    occurrences of verbs and prepositions indicating action or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixa
    -0.16
    ohana
    -0.16
    bsub
    -0.16
    abaj
    -0.15
    enou
    -0.15
    ÙĦØ©
    -0.15
     Clash
    -0.15
    .Sdk
    -0.15
    ÑĥÑĪ
    -0.14
    arf
    -0.14
    POSITIVE LOGITS
     here
    0.16
     Lang
    0.15
    lang
    0.15
     Hey
    0.14
    oston
    0.14
     on
    0.14
    Hey
    0.14
     school
    0.14
     lang
    0.13
     besides
    0.13
    Act Density 0.003%

    No Known Activations