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

    Neuronpedia

    INDEX
    Explanations

    recurring themes of stealth and presence in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.78
    ValueStyle
    -0.75
    __":
    -0.72
    ":[{
    -0.71
    Derbyniad
    -0.70
    はじめに
    -0.70
    esgue
    -0.69
    endphp
    -0.67
     springfox
    -0.67
    setVerticalGroup
    -0.66
    POSITIVE LOGITS
     Always
    1.06
    Always
    1.04
    always
    1.00
     always
    0.96
     ALWAYS
    0.94
    deauna
    0.94
    Never
    0.89
    ALWAYS
    0.89
     never
    0.88
     Never
    0.88
    Act Density 0.232%

    No Known Activations