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

    Neuronpedia

    INDEX
    Explanations

    technical jargon or terms related to specific fields or expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.16
     —↵↵
    -0.16
    .’↵↵
    -0.16
    üb
    -0.15
     ’
    -0.15
    Âł↵↵
    -0.15
    —↵↵
    -0.14
    !”↵↵
    -0.14
     âĢ¦↵↵
    -0.14
    ̧
    -0.14
    POSITIVE LOGITS
     Array
    0.32
     error
    0.22
     http
    0.22
     Error
    0.22
     ERROR
    0.20
     Http
    0.20
     png
    0.20
    Array
    0.19
     array
    0.19
     Hi
    0.19
    Act Density 0.005%

    No Known Activations