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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "holism" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nx
    -0.15
    dash
    -0.15
    icz
    -0.15
    etto
    -0.15
    sburg
    -0.14
    esimal
    -0.14
    nable
    -0.14
    овÑĭй
    -0.14
     Cobra
    -0.14
    razy
    -0.14
    POSITIVE LOGITS
     hol
    0.23
     Hol
    0.23
    ocaust
    0.20
    istic
    0.20
    mium
    0.20
    omorphic
    0.19
    mega
    0.19
    Hol
    0.18
    ocene
    0.18
    ubar
    0.18
    Act Density 0.012%

    No Known Activations