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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a strong emotional or conceptual depth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lum
    -0.17
    adc
    -0.16
    itian
    -0.16
    iras
    -0.16
    ãĥ¼ãĥ©
    -0.15
    zyst
    -0.15
    ãĥĨãĥ«
    -0.14
    olum
    -0.14
    ific
    -0.14
    rello
    -0.14
    POSITIVE LOGITS
    ening
    0.36
     deep
    0.36
    deep
    0.34
    -root
    0.32
    ened
    0.31
    Deep
    0.29
     deepest
    0.28
     Deep
    0.28
    æ·±
    0.28
     depths
    0.28
    Act Density 0.043%

    No Known Activations