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

    Neuronpedia

    INDEX
    Explanations

    words related to providing assistance, backing, or endorsing

    oai_token-act-pair · gpt-3.5-turbo

    references to support or opposition regarding various topics or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terness
    -0.88
     teasp
    -0.70
    cffffcc
    -0.69
    ixtape
    -0.67
    orp
    -0.67
    suits
    -0.66
    ngth
    -0.66
    pmwiki
    -0.66
    apeake
    -0.66
    bourne
    -0.65
    POSITIVE LOGITS
    enance
    0.79
     Supports
    0.76
     supporting
    0.71
    ORTS
    0.71
     Supporting
    0.70
    Support
    0.69
     him
    0.68
     them
    0.67
     reelection
    0.66
     independence
    0.66
    Act Density 0.053%

    No Known Activations