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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating quantity or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    the word "alone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anty
    -0.75
    acies
    -0.69
     Briggs
    -0.68
    olid
    -0.67
    arty
    -0.66
    enegger
    -0.65
    uay
    -0.64
     alignment
    -0.63
    EMP
    -0.63
     stances
    -0.62
    POSITIVE LOGITS
     suffice
    0.82
    åŃIJ
    0.70
     exceeds
    0.68
    è£ħ
    0.66
     alone
    0.66
    Render
    0.65
     admit
    0.65
     amounted
    0.65
    è¦
    0.64
     justifies
    0.63
    Act Density 0.019%

    No Known Activations