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

    Neuronpedia

    INDEX
    Explanations

    prepositions starting with 'about' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "about."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itus
    -0.73
    à¥
    -0.73
    rang
    -0.71
    achus
    -0.70
    rift
    -0.68
    ocaly
    -0.68
    oppy
    -0.67
    hesis
    -0.63
    olly
    -0.62
    ãĤ¿
    -0.62
    POSITIVE LOGITS
     Vega
    0.64
    mosp
    0.61
    PsyNetMessage
    0.59
     fairness
    0.59
     how
    0.59
     NX
    0.58
     ..........
    0.58
     Vulkan
    0.57
    =>
    0.57
     Polaris
    0.54
    Act Density 0.055%

    No Known Activations