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

    Neuronpedia

    INDEX
    Explanations

    the presence of progressive verbs and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /remove
    -0.24
    /delete
    -0.20
    avr
    -0.18
    /write
    -0.18
    /disable
    -0.17
    heimer
    -0.17
    ÂŃing
    -0.17
    /read
    -0.16
    /change
    -0.16
    ings
    -0.16
    POSITIVE LOGITS
    /loading
    0.23
    ly
    0.23
    /testing
    0.19
    /logging
    0.17
    g
    0.16
    LY
    0.16
     toward
    0.15
     Verg
    0.15
    redient
    0.15
    redients
    0.15
    Act Density 0.452%

    No Known Activations