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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority figures and established positions in a hierarchical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áce
    -0.15
    ajes
    -0.15
     suck
    -0.14
    ÑģÑĤе
    -0.14
    åŃĿ
    -0.14
    anco
    -0.13
    PEAR
    -0.13
    ñas
    -0.13
    ografie
    -0.13
     оÑĢганиза
    -0.13
    POSITIVE LOGITS
     trÆ°á»Łng
    0.20
     marshal
    0.19
    ancellor
    0.19
    utenant
    0.18
    intendent
    0.18
    ographer
    0.17
    ervisor
    0.17
    ordinator
    0.16
    istrator
    0.16
     general
    0.15
    Act Density 0.119%

    No Known Activations