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

    Neuronpedia

    INDEX
    Explanations

    suffix patterns related to characteristics or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHANT
    -0.16
    ooter
    -0.16
     žal
    -0.16
    asti
    -0.15
    lever
    -0.15
    kins
    -0.15
    _REPEAT
    -0.15
    ĥ
    -0.15
    fone
    -0.14
    DNA
    -0.14
    POSITIVE LOGITS
     Han
    0.16
    670
    0.15
    493
    0.15
    926
    0.15
    acular
    0.15
     Georgia
    0.14
    568
    0.14
    560
    0.14
    329
    0.14
     éĢ
    0.14
    Act Density 0.001%

    No Known Activations