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

    Neuronpedia

    INDEX
    Explanations

    certain academic or research-related terminology and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    459
    -0.18
    ungs
    -0.17
    yr
    -0.16
    sob
    -0.15
    odie
    -0.15
    isma
    -0.15
    agr
    -0.15
    zdy
    -0.15
     Sob
    -0.15
    tp
    -0.15
    POSITIVE LOGITS
    opus
    0.18
    ega
    0.18
    ousel
    0.16
    ξι
    0.16
    /module
    0.15
    olean
    0.15
    asic
    0.14
    itled
    0.14
    ener
    0.14
    ansk
    0.14
    Act Density 0.017%

    No Known Activations