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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥij
    -0.16
    berger
    -0.16
    rowad
    -0.15
    /Framework
    -0.15
    _boundary
    -0.14
    ãĥ³ãĥĹ
    -0.14
    ovich
    -0.14
    _EXTERN
    -0.14
    iedy
    -0.14
    isoner
    -0.14
    POSITIVE LOGITS
     intermediate
    0.36
     Intermediate
    0.32
     intermedi
    0.32
     intermediary
    0.30
    Intermediate
    0.27
     intervening
    0.27
     interim
    0.22
     trung
    0.20
    (inter
    0.19
    ระหว
    0.18
    Act Density 0.102%

    No Known Activations