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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "involvement" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quential
    -0.16
    .scalablytyped
    -0.15
    ahoo
    -0.14
    erah
    -0.14
    igi
    -0.14
    å²
    -0.14
     McKenzie
    -0.14
    BITS
    -0.13
    arshal
    -0.13
    umer
    -0.13
    POSITIVE LOGITS
     Dream
    0.17
    atten
    0.15
    ัà¸ķà¸ĸ
    0.15
     sacrifice
    0.14
    ivet
    0.14
    esson
    0.14
    amik
    0.14
     mortar
    0.14
    FAULT
    0.13
    ymi
    0.13
    Act Density 0.032%

    No Known Activations