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

    Neuronpedia

    INDEX
    Explanations

    short phrases or keywords related to political events and figures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and conjunctions in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.80
     guiActiveUnfocused
    -0.67
    iami
    -0.67
    liga
    -0.66
    ulla
    -0.65
    rift
    -0.64
    rica
    -0.63
    elf
    -0.61
    uce
    -0.60
    ighed
    -0.60
    POSITIVE LOGITS
     namely
    1.70
     viz
    1.31
     albeit
    0.96
     whereby
    0.85
     though
    0.85
     besides
    0.81
     however
    0.75
     although
    0.74
     wherein
    0.74
     insofar
    0.71
    Act Density 0.300%

    No Known Activations