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

    Neuronpedia

    INDEX
    Explanations

    terms related to correctness and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laz
    -0.17
    thing
    -0.17
    ç±į
    -0.17
    edeki
    -0.16
    antha
    -0.15
    sWith
    -0.15
    ello
    -0.15
    dish
    -0.15
    ers
    -0.15
    ÙĬ
    -0.15
    POSITIVE LOGITS
    itude
    0.18
    ponible
    0.17
    zza
    0.16
     representations
    0.16
    Representation
    0.15
    addock
    0.15
    ives
    0.15
    intl
    0.15
     portrayal
    0.15
    çİĩ
    0.15
    Act Density 0.020%

    No Known Activations