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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals and their roles or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sahiptir
    -0.54
     bleef
    -0.52
     göre
    -0.50
     terdengar
    -0.50
    GOT
    -0.48
    מיד
    -0.47
     descobri
    -0.47
     mourut
    -0.46
     gevoel
    -0.46
    意思是
    -0.46
    POSITIVE LOGITS
     unfold
    1.01
     coming
    0.84
     emerge
    0.82
     evolve
    0.82
     perform
    0.76
     operate
    0.75
     grow
    0.74
     come
    0.73
     happen
    0.72
     unfolding
    0.72
    Act Density 0.209%

    No Known Activations