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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating substitution or replacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ells
    -0.77
     Dynamics
    -0.66
     Skies
    -0.65
     Rebell
    -0.64
     Drift
    -0.60
    knit
    -0.60
     damned
    -0.60
     Beans
    -0.59
    istor
    -0.58
    izoph
    -0.58
    POSITIVE LOGITS
     thereof
    1.11
    itial
    0.76
    ngth
    0.75
    uations
    0.75
    INGTON
    0.73
     lieu
    0.72
    uary
    0.71
    aldehyde
    0.70
     guiActiveUn
    0.70
    isons
    0.69
    Act Density 0.005%

    No Known Activations