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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

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

    phrases containing themselves or respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁢
    -0.38
    his
    -0.37
    AISSEE
    -0.36
    ValueStyle
    -0.35
    彼の
    -0.35
    slash
    -0.35
    inetic
    -0.35
    PathParam
    -0.35
    ')";
    -0.35
    athletic
    -0.35
    POSITIVE LOGITS
     respectively
    0.63
     themselves
    0.57
     respectivement
    0.54
    DockStyle
    0.54
    BeginContext
    0.53
     CreateTagHelper
    0.52
    themselves
    0.52
    respectively
    0.50
    IntoConstraints
    0.50
     respectivamente
    0.50
    Act Density 0.148%

    No Known Activations