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

    Neuronpedia

    INDEX
    Explanations

    references to mid-range or intermediate measurements in various contexts

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

    mid-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.75
     HasFactory
    -0.75
     myſelf
    -0.73
    batore
    -0.69
    cinogenicity
    -0.67
     المعيارى
    -0.61
    LEncoder
    -0.59
     ſich
    -0.59
     Anſ
    -0.59
    ſelf
    -0.59
    POSITIVE LOGITS
     Mid
    0.79
     mid
    0.78
    Mid
    0.77
    mid
    0.58
     MID
    0.54
     Middle
    0.51
    MID
    0.49
     mids
    0.49
     early
    0.48
     Mitte
    0.48
    Act Density 0.010%

    No Known Activations