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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and apostrophes

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

    Single quote followed by "cause"

    np_acts-logits-general · gemini-2.0-flash

    'cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.72
    mybatisplus
    -0.71
     ***!
    -0.69
    хьтан
    -0.67
     bezeichneter
    -0.67
    IntoConstraints
    -0.67
    DockStyle
    -0.67
     مرئيه
    -0.66
    guenos
    -0.66
    utilisons
    -0.65
    POSITIVE LOGITS
    cause
    0.63
     ’
    0.54
    til
    0.52
    "'
    0.47
    glog
    0.46
     "'
    0.45
    tis
    0.44
    ूम
    0.43
    “
    0.42
    ribune
    0.42
    Act Density 0.253%

    No Known Activations