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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "separate."

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

    separate followed by a distinct item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IconModule
    -0.56
    IntoConstraints
    -0.51
    Tracce
    -0.49
    sendLogPayload
    -0.48
    stylers
    -0.48
    charCode
    -0.46
     ComVisible
    -0.46
    hasError
    -0.46
    Демографія
    -0.46
     AppBar
    -0.44
    POSITIVE LOGITS
     separate
    1.11
    separate
    1.02
    Separate
    0.98
     Separate
    0.96
     seperate
    0.89
     separately
    0.85
     SEPAR
    0.77
     separat
    0.75
     separado
    0.70
     ayrı
    0.69
    Act Density 0.011%

    No Known Activations