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

    Neuronpedia

    INDEX
    Explanations

    significant claims or statements that seem improbable or extraordinary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspecified
    -0.16
    eniable
    -0.15
    ÏĢοÏĦε
    -0.15
    ynn
    -0.15
    ektor
    -0.15
     ÑįÑĦÑĦек
    -0.14
    enderror
    -0.14
     undecided
    -0.14
    icontrol
    -0.14
     inde
    -0.14
    POSITIVE LOGITS
    Impossible
    0.22
    unlikely
    0.22
     impossible
    0.20
     odds
    0.20
     unlikely
    0.20
     Impossible
    0.20
     improbable
    0.19
     impro
    0.18
     imposs
    0.18
     aud
    0.18
    Act Density 0.176%

    No Known Activations