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

    Neuronpedia

    INDEX
    Explanations

    references to government and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç
    -0.15
    ive
    -0.15
    ard
    -0.15
    ctl
    -0.15
    ore
    -0.15
     imagination
    -0.14
    went
    -0.14
    hz
    -0.14
    ier
    -0.14
    ally
    -0.14
    POSITIVE LOGITS
     exact
    0.24
     move
    0.24
    Exact
    0.18
     moves
    0.18
     precise
    0.18
    exact
    0.17
    move
    0.17
     Epoch
    0.17
     announcement
    0.17
    timing
    0.16
    Act Density 0.113%

    No Known Activations