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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rank or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edback
    -0.17
    ESCO
    -0.16
    esco
    -0.15
    ahren
    -0.15
    aurus
    -0.15
     siguientes
    -0.14
    زد
    -0.14
    folio
    -0.14
     various
    -0.14
    ह
    -0.14
    POSITIVE LOGITS
     norm
    0.27
     only
    0.24
     stuff
    0.24
     fault
    0.22
     pits
    0.22
     reason
    0.21
     opposite
    0.21
    norm
    0.21
     case
    0.20
     ONLY
    0.19
    Act Density 0.130%

    No Known Activations