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

    Neuronpedia

    INDEX
    Explanations

    code snippets or code-related terms.

    oai_token-act-pair · gemini-2.0-flash

    unrecognized or malformed code patterns

    np_token-act-pair-logits · gpt-4o-mini

    Code and markup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.66
     d
    -0.60
    ↵↵
    -0.59
     di
    -0.58
     s
    -0.58
     t
    -0.57
     F
    -0.56
     von
    -0.56
     D
    -0.56
     he
    -0.56
    POSITIVE LOGITS
    AndEndTag
    0.97
    AddTagHelper
    0.93
     Theſe
    0.91
     myſelf
    0.90
     itſelf
    0.90
    ValueStyle
    0.89
     pleaſure
    0.87
     houſe
    0.86
     '\\;'
    0.86
     Monfieur
    0.84
    Act Density 7.618%

    No Known Activations