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

    Neuronpedia

    INDEX
    Explanations

    references to uncertainty or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utherland
    -0.18
    lsru
    -0.17
    -vs
    -0.16
    sv
    -0.15
    erece
    -0.14
     Bones
    -0.14
    arÃŃa
    -0.14
     åį
    -0.14
    ((*
    -0.14
    aversable
    -0.14
    POSITIVE LOGITS
    uble
    0.16
    \Configuration
    0.15
    -ignore
    0.15
    اÙĬÙĦ
    0.15
     Casey
    0.14
     chron
    0.14
    cron
    0.14
     Premi
    0.14
    ãģĹãĤĩ
    0.14
     Canter
    0.14
    Act Density 0.065%

    No Known Activations