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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community feedback and communication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    /-
    -0.74
    iasis
    -0.64
    anish
    -0.61
     disqualified
    -0.60
    zik
    -0.59
    uates
    -0.58
    eele
    -0.57
    inguished
    -0.57
    ativity
    -0.57
     terminated
    -0.56
    POSITIVE LOGITS
     twitter
    0.87
     forums
    0.81
     Twitter
    0.78
    amph
    0.69
    pless
    0.68
     Instagram
    0.68
     Facebook
    0.66
     Forums
    0.66
     social
    0.65
     market
    0.63
    Act Density 0.039%

    No Known Activations