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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organizations and councils

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations and councils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocence
    -0.68
     innoc
    -0.67
     lashes
    -0.64
     revenge
    -0.64
     torment
    -0.64
     rage
    -0.64
     outburst
    -0.63
     onlook
    -0.61
    lash
    -0.61
     remorse
    -0.61
    POSITIVE LOGITS
     headquartered
    0.84
     Corporation
    0.78
     hereby
    0.76
     Publication
    0.76
     Headquarters
    0.75
     Faculty
    0.74
     Instit
    0.73
     Integrated
    0.73
     subsidiaries
    0.72
     accredited
    0.72
    Act Density 1.237%

    No Known Activations