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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and expressions, particularly those involving conditionals and variable checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !'
    -0.50
    !’
    -0.46
    !}
    -0.45
    !”
    -0.43
    !',
    -0.43
    2
    -0.43
    !",
    -0.41
    !<
    -0.41
    !!!
    -0.41
    !!!"
    -0.40
    POSITIVE LOGITS
    (((
    0.60
    ((
    0.59
    ((*
    0.58
    (__
    0.57
    (*
    0.56
    (_
    0.55
    ([]
    0.53
    ((&
    0.53
    (!__
    0.49
    (*(
    0.49
    Act Density 0.146%

    No Known Activations