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

    Neuronpedia

    INDEX
    Explanations

    negative signs or symbols used in formatting or coding contexts

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

    citations like [-@robins]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.62
    transQ
    -0.62
    __':
    -0.57
    findpost
    -0.57
    Clik
    -0.55
    ➯
    -0.54
    GenerationType
    -0.53
     NgModule
    -0.53
    hitheatre
    -0.53
    ++){
    -0.53
    POSITIVE LOGITS
    [-
    0.87
    [:-
    0.70
     vorige
    0.65
     [-
    0.61
    ][-
    0.60
     viime
    0.59
     last
    0.54
     letzten
    0.54
    ([-
    0.54
    last
    0.53
    Act Density 0.010%

    No Known Activations