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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing or refuting statements or claims

    oai_token-act-pair · gpt-3.5-turbo

    the word "about" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hesis
    -0.88
    OGR
    -0.85
    quez
    -0.82
    rift
    -0.79
    chnology
    -0.76
    terness
    -0.73
    hetics
    -0.73
    KC
    -0.71
    >>>>>>>>
    -0.71
    mouth
    -0.69
    POSITIVE LOGITS
     how
    1.05
     whether
    0.93
     reforming
    0.82
     wanting
    0.80
     why
    0.80
     improving
    0.80
     needing
    0.79
     preventing
    0.78
     respecting
    0.77
     changing
    0.76
    Act Density 0.132%

    No Known Activations