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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "form" and its variations, indicating a focus on creation or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.17
    uti
    -0.16
     Gaul
    -0.15
    imal
    -0.15
    arial
    -0.15
    itz
    -0.14
    noop
    -0.14
    ary
    -0.14
    rocket
    -0.14
    ette
    -0.14
    POSITIVE LOGITS
    ulating
    0.18
    ulates
    0.17
    .scalablytyped
    0.15
    adius
    0.15
     basis
    0.15
    stride
    0.15
    sWith
    0.15
    dehyde
    0.15
    uster
    0.14
    urer
    0.14
    Act Density 0.029%

    No Known Activations