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

    Neuronpedia

    INDEX
    Explanations

    words related to concerns or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.17
    ame
    -0.15
    gere
    -0.15
     borr
    -0.14
    zac
    -0.14
    ero
    -0.14
    alion
    -0.14
     Dumpster
    -0.14
    experience
    -0.14
    ourke
    -0.14
    POSITIVE LOGITS
    lessly
    0.18
     ìĤ¬íķŃ
    0.16
     Concern
    0.15
    /conf
    0.15
    _TI
    0.14
    amel
    0.14
     hã
    0.14
    ìĤ¬íķŃ
    0.14
     Hen
    0.13
    EditText
    0.13
    Act Density 0.042%

    No Known Activations