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

    Neuronpedia

    INDEX
    Explanations

    information related to controversies or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas, indicating the structure of complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vised
    -0.72
    FW
    -0.71
    ãĥīãĥ©
    -0.70
    ops
    -0.69
    ofer
    -0.67
    enz
    -0.66
    Ö¼
    -0.65
    ibe
    -0.64
    role
    -0.64
    aque
    -0.64
    POSITIVE LOGITS
     tensions
    0.86
     rumors
    0.77
     culminating
    0.75
     rumours
    0.73
     expect
    0.67
     however
    0.67
     reminding
    0.66
     pundits
    0.66
     there
    0.66
     it
    0.65
    Act Density 0.253%

    No Known Activations