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

    Neuronpedia

    INDEX
    Explanations

    instances where something is explained as being a result of multiple factors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating partial causation or partial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.97
    eers
    -0.92
    ERY
    -0.84
    ciating
    -0.81
    Trend
    -0.76
    endi
    -0.75
    SHIP
    -0.74
     clipboard
    -0.72
    ãĥ¤
    -0.71
    gently
    -0.70
    POSITIVE LOGITS
     cloudy
    0.86
     obscured
    0.83
     overlapping
    0.70
     veiled
    0.69
     reflecting
    0.68
     fueled
    0.66
     opaque
    0.65
     blinded
    0.64
     attributed
    0.64
     overlooked
    0.63
    Act Density 0.013%

    No Known Activations