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

    Neuronpedia

    INDEX
    Explanations

    words related to fear and apprehension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.17
    ilter
    -0.16
    iferay
    -0.16
    anness
    -0.15
    ependency
    -0.15
    quirer
    -0.15
    rane
    -0.15
    gers
    -0.15
    kits
    -0.14
    arian
    -0.14
    POSITIVE LOGITS
    lessly
    0.36
     hã
    0.29
    fully
    0.26
    mong
    0.26
    fulness
    0.23
    ful
    0.23
     Fear
    0.21
    æĢĸ
    0.20
    Fear
    0.19
    less
    0.19
    Act Density 0.016%

    No Known Activations