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

    Neuronpedia

    INDEX
    Explanations

    structured formats or patterns in text, particularly in questions and answer options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iac
    -0.15
    iar
    -0.14
    ores
    -0.14
    ium
    -0.14
    iam
    -0.13
    ã
    -0.13
     Premi
    -0.13
    cow
    -0.13
    éŁ¿
    -0.13
    oba
    -0.13
    POSITIVE LOGITS
    ecz
    0.16
    -none
    0.15
    markup
    0.14
    olini
    0.14
    ожд
    0.14
    گراÙĨ
    0.14
    #ga
    0.13
    ertino
    0.13
    GRAM
    0.13
     cri
    0.13
    Act Density 0.005%

    No Known Activations