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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jug
    -0.16
     Frankie
    -0.14
     Bowl
    -0.14
    ardin
    -0.14
    orb
    -0.14
    ucu
    -0.14
     whereas
    -0.14
    emm
    -0.14
     pair
    -0.13
    iral
    -0.13
    POSITIVE LOGITS
    gio
    0.17
    otherwise
    0.16
     czy
    0.15
     otherwise
    0.15
    oui
    0.15
    446
    0.15
     jinak
    0.15
     hay
    0.14
    oub
    0.14
    ↵↵
    0.14
    Act Density 0.175%

    No Known Activations