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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertain situations or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express certainty or important statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continuum
    -0.65
     recy
    -0.65
    athered
    -0.61
     diffusion
    -0.59
    ĸļ
    -0.59
     reusable
    -0.58
     overlap
    -0.58
     collaps
    -0.57
     assemb
    -0.57
     descriptive
    -0.56
    POSITIVE LOGITS
     Instead
    0.82
     Therefore
    0.71
    Instead
    0.69
     Otherwise
    0.69
     Because
    0.68
     Maybe
    0.68
     Certainly
    0.66
     However
    0.66
    mere
    0.63
     Wouldn
    0.62
    Act Density 1.386%

    No Known Activations