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

    Neuronpedia

    INDEX
    Explanations

    words that denote inevitability or unavoidability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hao
    -0.77
    anim
    -0.77
    rooms
    -0.74
    inally
    -0.74
    earch
    -0.72
    ession
    -0.70
    ERAL
    -0.67
    enthal
    -0.65
    emouth
    -0.64
    eport
    -0.64
    POSITIVE LOGITS
     linked
    1.03
     intertwined
    0.95
     destabil
    0.89
     Dise
    0.87
     entangled
    0.84
     grav
    0.81
     intertw
    0.79
     harmed
    0.76
     tied
    0.74
     scar
    0.73
    Act Density 0.031%

    No Known Activations