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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing various topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    the word "about" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rift
    -0.80
    hesis
    -0.78
    chnology
    -0.78
    ãĤ¿
    -0.73
    quez
    -0.73
    åĽ
    -0.72
    terness
    -0.71
    GV
    -0.69
    ni
    -0.68
    chen
    -0.68
    POSITIVE LOGITS
     how
    0.85
     overcoming
    0.78
     reforming
    0.78
     halfway
    0.74
     conquering
    0.70
     topics
    0.67
     needing
    0.64
     hating
    0.64
     homosexuality
    0.64
     missing
    0.63
    Act Density 0.108%

    No Known Activations