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

    Neuronpedia

    INDEX
    Explanations

    phrases related to functionality and product performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !=(
    -0.14
    anson
    -0.14
    DataTable
    -0.14
    beck
    -0.14
    .comp
    -0.14
     zb
    -0.14
    gil
    -0.14
     Joi
    -0.13
    rzy
    -0.13
    onde
    -0.13
    POSITIVE LOGITS
     out
    0.45
     box
    0.36
     straight
    0.33
     gate
    0.31
     коÑĢоб
    0.30
     Box
    0.28
    box
    0.28
     Gate
    0.27
    straight
    0.27
     Straight
    0.27
    Act Density 0.047%

    No Known Activations