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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fear

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    issance
    -0.64
    abase
    -0.63
    eret
    -0.63
    iary
    -0.61
     converter
    -0.61
    ributes
    -0.59
    ellery
    -0.59
    anmar
    -0.59
    erent
    -0.59
    estone
    -0.59
    POSITIVE LOGITS
     heights
    0.88
     repr
    0.73
     ghosts
    0.69
     retribution
    0.64
     retaliation
    0.63
    76561
    0.63
     snakes
    0.62
     drowning
    0.61
     losing
    0.60
     ger
    0.57
    Act Density 16.883%

    No Known Activations