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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forward
    -1.70
    EXPORT
    -1.70
    conversion
    -1.56
    vir
    -1.45
    future
    -1.45
    hal
    -1.43
    ~/
    -1.40
    printStackTrace
    -1.40
    {})
    -1.40
    compat
    -1.38
    POSITIVE LOGITS
    ting
    1.65
    anges
    1.57
     decree
    1.57
    opter
    1.56
    hes
    1.55
    osaurs
    1.53
    ties
    1.49
     dream
    1.49
    hesis
    1.49
     thing
    1.44
    Act Density 0.394%

    No Known Activations