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

    Neuronpedia

    INDEX
    Explanations

    phrases related to location or position

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    teness
    -0.67
    iencies
    -0.66
    iken
    -0.60
     elaborate
    -0.59
     precedent
    -0.59
    uish
    -0.59
    UTH
    -0.59
     misuse
    -0.58
     breach
    -0.58
     whiff
    -0.58
    POSITIVE LOGITS
    abouts
    0.84
     headed
    0.77
     today
    0.76
     able
    0.76
     anymore
    0.75
    externalActionCode
    0.74
     going
    0.74
     willing
    0.74
     communicating
    0.74
     presently
    0.73
    Act Density 0.112%

    No Known Activations