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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating access or entry restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aval
    -0.16
     output
    -0.15
    inci
    -0.14
     Output
    -0.14
     outputs
    -0.14
    tach
    -0.14
    immel
    -0.14
    cÃŃ
    -0.13
     Emb
    -0.13
    æľĭ
    -0.13
    POSITIVE LOGITS
     entry
    0.62
     enter
    0.56
     entering
    0.55
     enters
    0.54
     entrance
    0.53
     Entry
    0.52
    -entry
    0.51
    è¿Ľåħ¥
    0.51
    entry
    0.49
    enter
    0.49
    Act Density 0.206%

    No Known Activations