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

    Neuronpedia

    INDEX
    Explanations

    words related to totality or entirety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    743
    -0.21
    nist
    -0.16
    Insensitive
    -0.15
    nie
    -0.15
    eled
    -0.15
     OTHERWISE
    -0.15
    idable
    -0.15
    cker
    -0.15
    liest
    -0.14
    trand
    -0.14
    POSITIVE LOGITS
    uding
    0.20
     except
    0.19
    except
    0.18
    ready
    0.18
    iez
    0.17
    geme
    0.17
    Except
    0.17
    avia
    0.17
    usion
    0.17
    ef
    0.16
    Act Density 0.010%

    No Known Activations