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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to numerical values and metrics within the context of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ys
    -0.18
    Exec
    -0.17
    AllowAnonymous
    -0.15
    bu
    -0.15
     exec
    -0.14
    enny
    -0.14
    iali
    -0.13
    FT
    -0.13
    åı£
    -0.13
    O
    -0.13
    POSITIVE LOGITS
    úc
    0.17
    fen
    0.15
    ruk
    0.15
    onas
    0.15
    BootApplication
    0.15
    fang
    0.15
     prostitutas
    0.14
     massaggi
    0.14
     kli
    0.14
    Ư
    0.14
    Act Density 0.008%

    No Known Activations