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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns and verbs indicating action or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agar
    -0.17
    afi
    -0.15
    olt
    -0.15
    quete
    -0.14
    inding
    -0.14
    بت
    -0.14
    lod
    -0.14
    asti
    -0.13
    áºł
    -0.13
    ØŃÙĦ
    -0.13
    POSITIVE LOGITS
    heiro
    0.15
    ekyll
    0.15
    UNUSED
    0.15
    ocomplete
    0.14
    uent
    0.14
    stup
    0.14
    .Abstractions
    0.14
    /gpl
    0.14
     Walsh
    0.14
    uentes
    0.14
    Act Density 0.000%

    No Known Activations