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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "as" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Improvements
    -0.61
     collision
    -0.59
     hinge
    -0.59
     resulting
    -0.57
     Extensions
    -0.56
     Utility
    -0.56
     bursts
    -0.55
     Extension
    -0.55
     watershed
    -0.54
     Cabinet
    -0.53
    POSITIVE LOGITS
    ylum
    0.96
    ari
    0.86
    pect
    0.80
    oci
    0.79
    uran
    0.79
    urion
    0.78
    part
    0.76
    ional
    0.75
    pid
    0.75
    pir
    0.73
    Act Density 0.051%

    No Known Activations