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

    Neuronpedia

    INDEX
    Explanations

    references to path specifications and string escaping issues in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymm
    -0.17
    nore
    -0.16
    apter
    -0.16
    ë§ģ
    -0.15
     MainForm
    -0.15
    nemonic
    -0.14
    åĢĴ
    -0.14
    yme
    -0.14
    ë§ī
    -0.14
    esel
    -0.14
    POSITIVE LOGITS
     escaped
    0.24
     escaping
    0.23
     escape
    0.22
    escape
    0.21
    escaping
    0.20
     esc
    0.20
     escapes
    0.19
    _esc
    0.19
     literal
    0.19
    .escape
    0.19
    Act Density 0.183%

    No Known Activations