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

    Neuronpedia

    INDEX
    Explanations

    formal structures or indicators of procedures in a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     c
    -0.15
     ed
    -0.15
     m
    -0.14
     ch
    -0.14
     bl
    -0.14
     I
    -0.14
     The
    -0.14
    's
    -0.14
     fr
    -0.14
     int
    -0.14
    POSITIVE LOGITS
    Ngh
    0.17
    atego
    0.16
     célib
    0.16
    etur
    0.15
    ayne
    0.14
    reeze
    0.14
    iVar
    0.14
    OUNDS
    0.14
    ayet
    0.14
    obook
    0.14
    Act Density 0.088%

    No Known Activations