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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use of physical force

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the use of force in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    algia
    -0.78
     Hop
    -0.75
    alam
    -0.73
    axter
    -0.73
    roma
    -0.69
    erest
    -0.69
     Neighborhood
    -0.69
    Hop
    -0.68
     Correspond
    -0.68
    STER
    -0.68
    POSITIVE LOGITS
     force
    0.94
     maj
    0.90
     diseng
    0.83
    bang
    0.82
    fully
    0.81
    fulness
    0.80
     Awakens
    0.79
     eleph
    0.77
    ful
    0.76
     multiplier
    0.75
    Act Density 0.019%

    No Known Activations