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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress and forward movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kö
    -0.16
    Ìģc
    -0.15
    olie
    -0.15
    à¥ľ
    -0.14
    kit
    -0.14
    elder
    -0.14
     vrai
    -0.14
    kowski
    -0.14
    kat
    -0.14
     vero
    -0.14
    POSITIVE LOGITS
    ward
    0.20
    /back
    0.20
    wards
    0.20
    -thinking
    0.19
    /down
    0.17
    /up
    0.16
    forward
    0.14
    edList
    0.14
    ilenames
    0.14
    SSIP
    0.14
    Act Density 0.042%

    No Known Activations