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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt or questioning certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.58
    énario
    -0.56
    sigkeit
    -0.55
    uvwxyz
    -0.55
    !("{
    -0.52
     sagde
    -0.51
    ADELPHIA
    -0.51
    orsch
    -0.51
    isement
    -0.49
    <<<<<<<
    -0.48
    POSITIVE LOGITS
     Undoubtedly
    1.01
     undoubtedly
    0.91
     undeniably
    0.89
    oubtedly
    0.86
     unquestionably
    0.85
     undeniable
    0.82
     indisputable
    0.75
     undisputed
    0.74
     doubt
    0.73
     admit
    0.73
    Act Density 0.334%

    No Known Activations