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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     –
    -0.19
     («
    -0.18
     «
    -0.17
     âĢķ
    -0.16
     —
    -0.15
    Âł
    -0.14
    «
    -0.14
    !»
    -0.14
    Âĸ
    -0.13
     –↵
    -0.13
    POSITIVE LOGITS
    Telephone
    0.23
     Telephone
    0.22
     telephone
    0.20
    Clip
    0.19
     talked
    0.18
    telephone
    0.18
     Reaction
    0.18
     Witnesses
    0.17
    Viewer
    0.16
     Portions
    0.16
    Act Density 0.006%

    No Known Activations