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

    Neuronpedia

    INDEX
    Explanations

    terms related to gravity and its influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     näin
    -0.61
    excellents
    -0.60
    WithMany
    -0.58
    amatkan
    -0.58
     habet
    -0.57
     poffe
    -0.57
    TabIndex
    -0.56
    appartamento
    -0.56
    selves
    -0.55
    loys
    -0.55
    POSITIVE LOGITS
     gravity
    3.40
    gravity
    3.06
     Gravity
    3.02
    Gravity
    2.90
     GRAV
    2.12
     gravitational
    1.91
    GRAV
    1.85
     gravitation
    1.70
     grav
    1.63
     gravedad
    1.61
    Act Density 0.092%

    No Known Activations