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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a range or variety

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.97
    TagMode
    -0.79
    ortunadamente
    -0.75
    Filmografie
    -0.69
    UIControlState
    -0.68
     становника
    -0.67
    Filmographie
    -0.67
    \"]
    -0.67
    plaatst
    -0.66
    Faults
    -0.66
    POSITIVE LOGITS
     wolle
    0.51
     SEDS
    0.48
     defStyleAttr
    0.48
     they
    0.48
    ged
    0.46
     Sla
    0.45
     further
    0.44
     utafitiHapana
    0.44
     we
    0.44
     gew
    0.44
    Act Density 0.010%

    No Known Activations