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

    Neuronpedia

    INDEX
    Explanations

    specific articles and prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sterling
    -0.71
     Warn
    -0.67
     WARNING
    -0.67
     Aires
    -0.64
    gerald
    -0.62
    osate
    -0.61
    ij士
    -0.60
    gart
    -0.60
     WARN
    -0.60
     confir
    -0.59
    POSITIVE LOGITS
    portation
    0.87
    mission
    0.87
    sect
    0.86
    quel
    0.86
    unda
    0.84
    ample
    0.79
    cient
    0.78
    isphere
    0.77
    ãĥ¥
    0.76
    ced
    0.76
    Act Density 0.005%

    No Known Activations