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

    Neuronpedia

    INDEX
    Explanations

    phrases related to informing or sharing information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "about."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rift
    -0.81
    OGR
    -0.79
    à¥
    -0.73
    hesis
    -0.71
    waters
    -0.70
    ³³³³
    -0.70
    gallery
    -0.69
    ा
    -0.66
    CHR
    -0.66
    ³³³³³³³³³³³³³³³³
    -0.65
    POSITIVE LOGITS
     how
    0.76
     reforming
    0.74
     bund
    0.72
     certs
    0.65
     improving
    0.64
     whether
    0.64
     halfway
    0.63
     Zika
    0.63
    PsyNetMessage
    0.62
     Bund
    0.61
    Act Density 0.103%

    No Known Activations