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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "dis" indicating a state of negation or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venes
    -0.17
    edom
    -0.16
     mÃŃ
    -0.16
    onec
    -0.15
     Niet
    -0.15
    ins
    -0.15
    ahoma
    -0.15
    ices
    -0.15
    tir
    -0.14
    yles
    -0.14
    POSITIVE LOGITS
    .dis
    0.21
     Dis
    0.21
     dis
    0.20
    Grace
    0.20
    (dis
    0.20
    -dis
    0.18
    /dis
    0.18
    washer
    0.18
     Grace
    0.18
     grace
    0.18
    Act Density 0.031%

    No Known Activations