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

    Neuronpedia

    INDEX
    Explanations

    mentions of something happening or existing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "There" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.79
     versa
    -0.70
    rouse
    -0.67
    itud
    -0.64
    ologically
    -0.64
     ted
    -0.63
    CU
    -0.63
     traged
    -0.63
     consequ
    -0.62
     implants
    -0.61
    POSITIVE LOGITS
    chwitz
    0.82
    zbollah
    0.71
    undrum
    0.68
    reetings
    0.67
     Kanye
    0.67
    resa
    0.66
     Vegan
    0.65
    Wiki
    0.65
    anmar
    0.65
     Hear
    0.64
    Act Density 0.251%

    No Known Activations