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

    Neuronpedia

    INDEX
    Explanations

    elements related to timelines and historical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    195
    -0.21
    196
    -0.20
    194
    -0.20
     WWII
    -0.19
    193
    -0.19
    iaux
    -0.18
     Soviet
    -0.16
     twentieth
    -0.16
     Nazi
    -0.15
    dale
    -0.15
    POSITIVE LOGITS
    172
    0.72
    173
    0.71
    171
    0.70
    174
    0.69
    170
    0.68
    175
    0.67
    176
    0.65
    169
    0.62
    168
    0.61
    167
    0.59
    Act Density 0.101%

    No Known Activations