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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "title" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ño
    -0.16
    orf
    -0.16
    akin
    -0.15
    åĿª
    -0.15
    forming
    -0.15
    üstü
    -0.15
    zburg
    -0.14
    æķ£
    -0.14
    oir
    -0.14
    iams
    -0.14
    POSITIVE LOGITS
    ration
    0.24
    anic
    0.24
    mouse
    0.22
    ular
    0.21
    ulaire
    0.21
    illation
    0.21
    us
    0.20
    ulares
    0.20
    antic
    0.20
    ania
    0.19
    Act Density 0.009%

    No Known Activations