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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the condition or quality of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voks
    -0.16
    atti
    -0.15
    umph
    -0.15
    _BE
    -0.14
    acts
    -0.14
    rog
    -0.14
    ulence
    -0.14
    cht
    -0.13
    esty
    -0.13
     unsuccessful
    -0.13
    POSITIVE LOGITS
     condition
    0.73
     Condition
    0.63
    condition
    0.57
    Condition
    0.54
     CONDITION
    0.52
    -condition
    0.43
    _condition
    0.42
    .condition
    0.41
    CONDITION
    0.41
    (condition
    0.41
    Act Density 0.084%

    No Known Activations