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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mouth
    -0.85
    icide
    -0.77
    illus
    -0.76
    ican
    -0.74
    heit
    -0.73
    initialized
    -0.73
    yout
    -0.72
    ices
    -0.71
    TPPStreamerBot
    -0.71
    bush
    -0.70
    POSITIVE LOGITS
     afar
    1.36
     whence
    1.00
     scratch
    0.97
     outset
    0.88
     experience
    0.80
     Above
    0.77
     examining
    0.76
     standpoint
    0.75
     observing
    0.74
     watching
    0.73
    Act Density 0.040%

    No Known Activations