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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional logic and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antt
    -0.16
    agli
    -0.16
    òng
    -0.15
    wap
    -0.15
    _UNUSED
    -0.15
    ¢åįķ
    -0.15
    iverz
    -0.14
    adele
    -0.14
    kyt
    -0.14
    dash
    -0.14
    POSITIVE LOGITS
     chances
    0.47
     then
    0.43
     odds
    0.39
    then
    0.39
     thì
    0.33
     maka
    0.31
     Odds
    0.31
     it
    0.30
     entonces
    0.30
     well
    0.29
    Act Density 0.231%

    No Known Activations