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

    Neuronpedia

    INDEX
    Explanations

    definite statements and expressions of certainty or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actually
    -1.33
    actually
    -1.25
     basically
    -1.14
    Actually
    -1.14
     Actually
    -1.13
     Basically
    -1.11
    Basically
    -1.11
     apparently
    -1.10
     ACTUALLY
    -1.07
    Essentially
    -1.04
    POSITIVE LOGITS
     bukan
    0.60
     alguna
    0.60
     alguma
    0.58
    ই
    0.54
    ঃ
    0.54
    unkt
    0.53
     kein
    0.53
     någon
    0.53
     SOMEONE
    0.53
     somebody
    0.53
    Act Density 0.242%

    No Known Activations