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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software installation instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.87
    çĶ°
    -0.81
    ptives
    -0.76
    TextColor
    -0.73
    waters
    -0.73
    ACTED
    -0.72
    Bey
    -0.71
    ONSORED
    -0.70
    TPP
    -0.69
    POS
    -0.69
    POSITIVE LOGITS
     behalf
    1.38
    coming
    1.13
    etime
    1.07
    shore
    1.05
    erous
    1.01
     occasion
    0.99
    sets
    0.97
    demand
    0.94
    yx
    0.93
    eness
    0.91
    Act Density 0.442%

    No Known Activations