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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or actions, possibly in a negative context such as mistakes or frustrations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    wake
    -0.48
    nostic
    -0.47
    urden
    -0.46
    olphins
    -0.45
    card
    -0.45
    anza
    -0.44
    sson
    -0.44
    rain
    -0.43
    iaz
    -0.43
     Crane
    -0.43
    POSITIVE LOGITS
    rogen
    0.63
    rogens
    0.63
     then
    0.57
     forth
    0.55
    romeda
    0.54
     consequently
    0.52
    alus
    0.52
     heals
    0.51
     parcel
    0.49
     THEN
    0.48
    Act Density 7.856%

    No Known Activations