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

    Neuronpedia

    INDEX
    Explanations

    words related to emphasizing a conclusion or consequence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Defenders
    -0.71
     Polo
    -0.68
    igger
    -0.64
     metro
    -0.59
    ridges
    -0.56
     Ones
    -0.56
     Klu
    -0.55
     Beaver
    -0.55
    abies
    -0.55
     steroids
    -0.55
    POSITIVE LOGITS
    forth
    1.27
    entimes
    0.96
     far
    0.94
    forward
    0.91
    ly
    0.89
    far
    0.84
    mask
    0.76
    lessly
    0.74
    othe
    0.71
    ç¥ŀ
    0.70
    Act Density 0.021%

    No Known Activations