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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts between ideas or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.15
    uard
    -0.14
    anou
    -0.14
    ez
    -0.14
    ί
    -0.14
    Overflow
    -0.14
    bah
    -0.14
    oris
    -0.14
    uÄį
    -0.14
    ãģĹãģ®
    -0.13
    POSITIVE LOGITS
     ourselves
    0.23
     yourself
    0.20
     everyone
    0.19
     anyone
    0.19
     everybody
    0.18
     those
    0.18
     us
    0.18
     anybody
    0.18
     myself
    0.18
    ourn
    0.17
    Act Density 0.309%

    No Known Activations