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

    Neuronpedia

    INDEX
    Explanations

    various types of procedural instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oth
    -0.18
    pt
    -0.15
    -unused
    -0.14
    uat
    -0.14
    59
    -0.14
    qa
    -0.14
    ha
    -0.13
     ch
    -0.13
    rew
    -0.13
    ano
    -0.13
    POSITIVE LOGITS
    abei
    0.16
    ãģĸ
    0.14
    iola
    0.14
    کاÙĨ
    0.14
    longleftrightarrow
    0.14
    ijken
    0.14
    0.13
    ëĭ¥
    0.13
    .Creator
    0.13
    ISON
    0.13
    Act Density 0.008%

    No Known Activations