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

    Neuronpedia

    INDEX
    Explanations

    words related to concealment or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñįн
    -0.15
     Grove
    -0.15
    licated
    -0.15
    edb
    -0.14
    lint
    -0.14
    opup
    -0.14
    ycin
    -0.14
    apo
    -0.14
    apore
    -0.14
    ensburg
    -0.14
    POSITIVE LOGITS
    pcion
    0.26
    ivers
    0.25
    iving
    0.24
    voir
    0.23
    pción
    0.23
    ivable
    0.23
    ives
    0.23
    aling
    0.22
    ptr
    0.22
    ited
    0.22
    Act Density 0.007%

    No Known Activations