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

    Neuronpedia

    INDEX
    Explanations

    references to the act of finding or discovering something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zien
    -0.59
    ⓧ
    -0.57
     observed
    -0.55
    querque
    -0.54
     Known
    -0.52
    Known
    -0.51
     Against
    -0.51
    khana
    -0.51
    ahn
    -0.50
     Observed
    -0.49
    POSITIVE LOGITS
     anywhere
    1.14
     somewhere
    1.01
     everywhere
    0.89
    anywhere
    0.88
     elsewhere
    0.85
     someplace
    0.83
     nowhere
    0.80
    somewhere
    0.76
     Anywhere
    0.76
    everywhere
    0.75
    Act Density 0.246%

    No Known Activations