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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'loyalty'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itoris
    -0.15
    uder
    -0.14
    ikh
    -0.14
     feeder
    -0.14
    ãĥĥãĥī
    -0.14
    ulpt
    -0.14
    ely
    -0.14
     SavaÅŁ
    -0.13
    nock
    -0.13
    ovich
    -0.13
    POSITIVE LOGITS
    vine
    0.16
     Honest
    0.15
    amps
    0.15
    Beam
    0.15
    饮
    0.14
    elere
    0.14
    éments
    0.14
    åĬĥ
    0.14
    vail
    0.14
    æıĽ
    0.13
    Act Density 0.005%

    No Known Activations