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

    Neuronpedia

    INDEX
    Explanations

    strong and urgent calls to action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to appeals or demands for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Subtle
    -0.76
     Surv
    -0.64
     Expect
    -0.59
     Spoiler
    -0.58
     NX
    -0.57
     vulner
    -0.56
     Petra
    -0.56
     ejac
    -0.55
     Ascension
    -0.54
     srfAttach
    -0.54
    POSITIVE LOGITS
     to
    0.81
    reprene
    0.80
     for
    0.77
    backs
    0.72
    back
    0.72
    irection
    0.69
     underway
    0.69
    byn
    0.65
    erity
    0.64
    emaker
    0.62
    Act Density 0.206%

    No Known Activations