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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or things that are yet to happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itre
    -0.15
    rador
    -0.15
    ixed
    -0.15
    agal
    -0.14
    bow
    -0.14
    ifer
    -0.14
    481
    -0.14
    skou
    -0.14
    thon
    -0.14
    uy
    -0.13
    POSITIVE LOGITS
    ovol
    0.16
    'gc
    0.15
    zon
    0.15
    -Cs
    0.15
    imson
    0.15
     AppState
    0.14
    ships
    0.14
    LEGRO
    0.14
     Constructors
    0.13
    oldemort
    0.13
    Act Density 0.005%

    No Known Activations