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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or subjective evaluations

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

    start of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.45
     uș
    -0.44
     itſelf
    -0.44
    iſter
    -0.44
    [::-
    -0.43
    hematical
    -0.43
    astéroïdes
    -0.43
    (&:
    -0.43
    +#+
    -0.43
    固
    -0.42
    POSITIVE LOGITS
    SharedDtor
    0.46
     surla
    0.45
    帖最后由
    0.39
    makeText
    0.38
    SequentialGroup
    0.38
     Cla
    0.37
    transQ
    0.36
    formen
    0.36
     BorderSide
    0.36
     isSet
    0.36
    Act Density 0.193%

    No Known Activations