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

    Neuronpedia

    INDEX
    Explanations

    words related to comparison and contrast

    oai_token-act-pair · gpt-3.5-turbo

    relationships between different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hack
    -0.66
    onom
    -0.58
    oret
    -0.57
     NAACP
    -0.56
     Gund
    -0.55
     Mik
    -0.54
     Pok
    -0.54
     PAC
    -0.53
     Rah
    -0.53
     Prosecut
    -0.53
    POSITIVE LOGITS
    */(
    0.78
    NetMessage
    0.67
    req
    0.65
     thereby
    0.64
    chers
    0.63
     respectively
    0.61
    heres
    0.61
    ··
    0.60
    arrow
    0.60
    units
    0.60
    Act Density 0.859%

    No Known Activations