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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions or confrontations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    atoon
    -0.72
    aware
    -0.72
    iba
    -0.71
     converge
    -0.71
    Ct
    -0.68
    nel
    -0.63
    artifacts
    -0.63
    ources
    -0.61
    ami
    -0.61
     offend
    -0.61
    POSITIVE LOGITS
     chance
    1.14
     opportunity
    1.07
     choice
    1.03
     thumbs
    0.96
     rundown
    0.84
    credit
    0.82
     leash
    0.82
     backstory
    0.79
     credit
    0.78
     gift
    0.78
    Act Density 0.115%

    No Known Activations