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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols commonly found in mathematical or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ramp
    -0.17
    ior
    -0.15
     steer
    -0.15
     bond
    -0.15
     line
    -0.15
     Zuk
    -0.14
     ab
    -0.14
     rotation
    -0.14
    OTES
    -0.14
    Inline
    -0.14
    POSITIVE LOGITS
    berger
    0.17
    á»Ļng
    0.16
    ảo
    0.16
    оÑĦ
    0.15
    mojom
    0.15
    strar
    0.15
    anto
    0.15
    stras
    0.15
    --------------------------------------------------------------------------↵
    0.14
    CASCADE
    0.14
    Act Density 0.000%

    No Known Activations