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

    Neuronpedia

    INDEX
    Explanations

    patterns in numeric and character sequences, particularly focusing on identifiers and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hexadecimal characters followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings, guids, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.06
     pleaſure
    -1.02
     Majefty
    -0.94
     greateſt
    -0.93
     itſelf
    -0.93
     iſt
    -0.93
     perſon
    -0.92
     ſtate
    -0.91
     Houſe
    -0.91
     houſe
    -0.91
    POSITIVE LOGITS
     po
    0.51
     Ha
    0.48
     Ca
    0.48
     mit
    0.48
     Po
    0.47
     Al
    0.46
     V
    0.44
     P
    0.43
     typelib
    0.43
    \{\\
    0.43
    Act Density 0.079%

    No Known Activations