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

    Neuronpedia

    INDEX
    Explanations

    terms related to absolute measurements or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -0.84
    GEBURTSDATUM
    -0.82
     Houſe
    -0.82
     Monfieur
    -0.82
     Theſe
    -0.82
    <unused43>
    -0.82
    <unused51>
    -0.81
     ſeine
    -0.81
    <unused42>
    -0.81
    <unused41>
    -0.81
    POSITIVE LOGITS
     participating
    0.68
     participate
    0.66
     absolute
    0.66
     participated
    0.62
    ↵↵
    0.57
    ,
    0.54
    particip
    0.54
     appropriate
    0.53
     absolutely
    0.52
     participates
    0.52
    Act Density 0.176%

    No Known Activations