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

    Neuronpedia

    INDEX
    Explanations

    significant terms associated with legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riday
    -0.16
    ç«
    -0.16
    esser
    -0.15
    åĤĻ
    -0.15
    dex
    -0.15
    еÑĢин
    -0.14
    privileged
    -0.14
     Lif
    -0.13
     insecure
    -0.13
    verity
    -0.13
    POSITIVE LOGITS
    ibold
    0.15
    ajs
    0.14
    bsolute
    0.14
    /host
    0.14
    gew
    0.14
     adresse
    0.14
    andler
    0.14
    eya
    0.14
    cow
    0.14
    geois
    0.14
    Act Density 0.001%

    No Known Activations