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

    Neuronpedia

    INDEX
    Explanations

    terms related to the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.20
    ekim
    -0.16
    eria
    -0.16
    ÑĢави
    -0.15
    ÃŃcul
    -0.15
    ém
    -0.14
    isma
    -0.14
    isel
    -0.14
    cv
    -0.14
    en
    -0.14
    POSITIVE LOGITS
    IRONMENT
    0.34
    iro
    0.27
    IRON
    0.26
    oyer
    0.25
    oron
    0.23
    lope
    0.23
    ir
    0.22
    iros
    0.21
    olved
    0.21
    iable
    0.21
    Act Density 0.007%

    No Known Activations