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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raf
    -0.17
     coun
    -0.17
    hl
    -0.16
    aco
    -0.15
     favoured
    -0.15
    Jam
    -0.15
     Mist
    -0.15
    alled
    -0.15
     armour
    -0.15
    arin
    -0.14
    POSITIVE LOGITS
     lumber
    0.21
     due
    0.20
     Ke
    0.20
    adge
    0.19
     famed
    0.18
     minded
    0.18
     bang
    0.17
     roster
    0.17
     yet
    0.17
    ONA
    0.17
    Act Density 0.273%

    No Known Activations