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

    Neuronpedia

    INDEX
    Explanations

    topics related to cracking or breaking, especially in physical or metaphorical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colette
    -0.78
     estadual
    -0.76
    icoot
    -0.72
     Pollack
    -0.69
     Aub
    -0.69
     Puck
    -0.68
    Bung
    -0.68
    Puck
    -0.68
     Dahlia
    -0.68
     Axiom
    -0.68
    POSITIVE LOGITS
     Sorensen
    0.92
     /\.
    0.84
    Linq
    0.82
     Slag
    0.81
     Macht
    0.74
     rval
    0.73
     McCormack
    0.72
     Игорь
    0.71
     préfé
    0.70
    ctools
    0.69
    Act Density 1.915%

    No Known Activations