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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inker
    -0.18
    ses
    -0.17
    ea
    -0.16
    yers
    -0.16
    hiba
    -0.16
    een
    -0.16
    hor
    -0.16
    mtree
    -0.15
    hes
    -0.15
    sj
    -0.15
    POSITIVE LOGITS
     else
    0.21
    Æ¡
    0.18
    onne
    0.16
    anging
    0.15
    theless
    0.15
    dock
    0.15
    lli
    0.14
    igator
    0.14
    anged
    0.14
    ly
    0.14
    Act Density 0.017%

    No Known Activations