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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a discussion or emphasis on a particular topic

    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
    -0.71
    gallery
    -0.66
    ocaly
    -0.64
     Peaks
    -0.63
    rang
    -0.62
    OGR
    -0.61
    ammy
    -0.60
    Released
    -0.60
    oland
    -0.58
    oulos
    -0.57
    POSITIVE LOGITS
     halfway
    0.77
    PsyNetMessage
    0.72
     respecting
    0.67
     how
    0.67
    sted
    0.61
     coerc
    0.60
     reforming
    0.59
    lihood
    0.59
     250
    0.58
    aleb
    0.58
    Act Density 0.154%

    No Known Activations