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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and phrases related to appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ches
    -0.17
     Ble
    -0.16
    Typed
    -0.15
    amon
    -0.14
    оÑĢож
    -0.14
    hape
    -0.14
    illon
    -0.14
     blackout
    -0.14
    .scalablytyped
    -0.14
    ewise
    -0.14
    POSITIVE LOGITS
     finish
    0.15
    ENCE
    0.15
    ãĥ¥
    0.15
    serial
    0.15
     PARTICULAR
    0.15
     bach
    0.14
    ifer
    0.14
     Armor
    0.14
     HOLDERS
    0.14
    iert
    0.14
    Act Density 0.043%

    No Known Activations