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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuation or progression in a process or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lesh
    -0.19
    stab
    -0.17
    abbo
    -0.17
     Jo
    -0.15
     off
    -0.15
    andas
    -0.15
    bell
    -0.15
    isyon
    -0.14
     inh
    -0.14
     back
    -0.14
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.17
     Interr
    0.16
    SSIP
    0.15
    eyin
    0.15
    ^K
    0.15
    DMIN
    0.15
    ergy
    0.14
     Rings
    0.14
     từng
    0.14
    ij¸
    0.14
    Act Density 0.091%

    No Known Activations