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

    Neuronpedia

    INDEX
    Explanations

    instances where actions are taken or decisions are made

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.88
    REDACTED
    -0.78
    glass
    -0.70
    Lens
    -0.70
    gravity
    -0.68
    cro
    -0.68
    chuk
    -0.66
    ministic
    -0.66
    alpha
    -0.66
    Pac
    -0.65
    POSITIVE LOGITS
     least
    1.20
    onement
    1.05
     halftime
    0.93
    rial
    0.86
     funer
    0.84
    abase
    0.83
     airports
    0.82
     times
    0.81
     home
    0.79
    yp
    0.79
    Act Density 0.248%

    No Known Activations