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

    Neuronpedia

    INDEX
    Explanations

    references to Earth and planetary themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egin
    -0.19
    eof
    -0.16
    ahat
    -0.16
    MBER
    -0.15
    utto
    -0.15
    voor
    -0.14
    erde
    -0.14
    Æł
    -0.14
    деÑĢ
    -0.14
    uty
    -0.14
    POSITIVE LOGITS
    quake
    0.40
    worm
    0.38
    lings
    0.36
    bound
    0.35
    ling
    0.29
    rise
    0.29
    shine
    0.28
    qu
    0.27
    moving
    0.27
     sciences
    0.27
    Act Density 0.021%

    No Known Activations