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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing mutual relationships and interactions between individuals

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

    "each other" or similar relational phrases

    np_acts-logits-general · gemini-2.0-flash

    each other, one another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.72
    SourceChecksum
    -0.70
    ']='
    -0.68
    "]}
    -0.67
    》.
    -0.66
    ]),
    -0.66
    ---*/
    -0.66
    '));
    -0.64
     rezerv
    -0.64
    )';
    -0.64
    POSITIVE LOGITS
    selves
    0.65
     المعيارى
    0.60
    ’
    0.54
    Externí
    0.54
    CompilerServices
    0.53
    brainly
    0.52
    ization
    0.49
     getItemCount
    0.48
    jaciół
    0.48
    argout
    0.48
    Act Density 0.066%

    No Known Activations