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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otta
    -0.14
    ragment
    -0.14
    γγ
    -0.13
    ossa
    -0.13
     Fabric
    -0.13
    ertools
    -0.13
    UEST
    -0.13
    enos
    -0.13
    lems
    -0.12
    arda
    -0.12
    POSITIVE LOGITS
    ekl
    0.15
    apus
    0.15
     Kauf
    0.15
    criptor
    0.15
    stype
    0.15
    ror
    0.14
     Guth
    0.14
    eko
    0.14
    bd
    0.14
    odesk
    0.14
    Act Density 0.102%

    No Known Activations