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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures or events related to monarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    189
    -0.17
     INTERRUPTION
    -0.17
    190
    -0.17
    ãĥ³ãĤ¬
    -0.16
    idunt
    -0.16
     Alfred
    -0.16
    191
    -0.16
    194
    -0.15
     pian
    -0.15
    187
    -0.15
    POSITIVE LOGITS
    161
    0.41
    162
    0.40
    164
    0.40
    166
    0.40
    163
    0.40
    159
    0.39
    165
    0.38
    167
    0.36
    160
    0.35
    169
    0.34
    Act Density 0.310%

    No Known Activations