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

    Neuronpedia

    INDEX
    Explanations

    political phrases or statements

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.78
     scattering
    -0.75
     unmarked
    -0.72
     scatter
    -0.70
     Grimoire
    -0.70
     diffusion
    -0.68
     decomp
    -0.68
     semic
    -0.66
     Unified
    -0.66
     confinement
    -0.66
    POSITIVE LOGITS
    ¹
    1.09
    Į
    0.92
    į
    0.91
    realDonaldTrump
    0.90
    ISIS
    0.90
    ı
    0.89
    trump
    0.89
    ¬
    0.88
    £
    0.87
    ¼
    0.86
    Act Density 0.545%

    No Known Activations