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

    Neuronpedia

    INDEX
    Explanations

    descriptions of expectations and typical behaviors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inder
    -0.14
    acs
    -0.14
    ori
    -0.14
    .pth
    -0.13
    ugin
    -0.13
    leaning
    -0.13
    ssa
    -0.13
    oder
    -0.13
     Burr
    -0.13
    lse
    -0.13
    POSITIVE LOGITS
     typical
    0.30
     classic
    0.26
    typ
    0.23
     Typical
    0.22
     tÃŃ
    0.21
     modern
    0.20
    Typ
    0.20
     Äijiá»ĥn
    0.19
    classic
    0.18
    åħ¸
    0.18
    Act Density 0.148%

    No Known Activations