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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of large gatherings or coming together of groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashington
    -0.83
    RELATED
    -0.73
    SPONSORED
    -0.71
    fulness
    -0.69
    acebook
    -0.67
    existent
    -0.65
    }}}
    -0.64
     risked
    -0.64
     âĢº
    -0.64
    atis
    -0.62
    POSITIVE LOGITS
     reinforcements
    0.86
     surprise
    0.77
     smelling
    0.72
     unexpectedly
    0.69
     hither
    0.68
     refreshed
    0.68
     doorstep
    0.66
     stronger
    0.65
     surprises
    0.65
     heels
    0.63
    Act Density 0.449%

    No Known Activations