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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate lesser-known or less frequently mentioned content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ento
    -0.17
    orman
    -0.14
     endemic
    -0.14
    ays
    -0.14
     surrounds
    -0.14
     FIG
    -0.14
    oded
    -0.13
     Fro
    -0.13
     Latest
    -0.13
     cheers
    -0.13
    POSITIVE LOGITS
    used
    0.24
     used
    0.23
     cited
    0.23
    _used
    0.22
    -used
    0.22
    known
    0.22
     USED
    0.22
    -known
    0.21
     known
    0.21
     loved
    0.20
    Act Density 0.091%

    No Known Activations