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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases expressing uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viks
    -0.81
    verts
    -0.80
    arius
    -0.75
    aukee
    -0.67
    vert
    -0.65
     srf
    -0.64
    ummies
    -0.64
    adra
    -0.63
    estones
    -0.62
     sacrific
    -0.61
    POSITIVE LOGITS
    yip
    0.64
     they
    0.62
    Enlarge
    0.61
    govtrack
    0.60
    PI
    0.60
     he
    0.60
    NetMessage
    0.58
    erred
    0.58
    lihood
    0.57
     she
    0.56
    Act Density 0.022%

    No Known Activations