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

    Neuronpedia

    INDEX
    Explanations

    commands or phrases indicating permission or allowance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edList
    -0.18
    erland
    -0.16
    rien
    -0.15
    edImage
    -0.15
    ÑĢаÑħ
    -0.15
    surname
    -0.15
    ivent
    -0.14
    edl
    -0.14
    ventus
    -0.14
    pectral
    -0.14
    POSITIVE LOGITS
    tings
    0.29
    ting
    0.27
     us
    0.25
     loose
    0.24
    ÃŃcia
    0.22
     go
    0.22
    tres
    0.20
    TING
    0.19
    itia
    0.19
     know
    0.19
    Act Density 0.032%

    No Known Activations