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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "what" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anything
    -0.16
     FindObjectOfType
    -0.15
    hiba
    -0.15
     anything
    -0.14
    emens
    -0.14
    ect
    -0.14
    Anything
    -0.14
    aises
    -0.14
    Ùĩ
    -0.14
    encer
    -0.13
    POSITIVE LOGITS
     do
    0.29
     else
    0.29
    soever
    0.28
     better
    0.25
    's
    0.23
     if
    0.22
    -ever
    0.21
     follows
    0.21
     about
    0.21
    ’s
    0.20
    Act Density 0.071%

    No Known Activations