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

    Neuronpedia

    INDEX
    Explanations

    instances of the suffix "-ist" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.57
     A
    -0.50
     O
    -0.49
     H
    -0.48
     P
    -0.48
    <bos>
    -0.47
    ti
    -0.47
    .
    -0.47
     D
    -0.46
     J
    -0.46
    POSITIVE LOGITS
    ſelf
    1.11
     myſelf
    1.11
     itſelf
    1.02
     ſta
    1.01
     ſtand
    0.98
     indígen
    0.97
    ſelves
    0.92
     increí
    0.92
     ſche
    0.91
    <unused43>
    0.90
    Act Density 0.403%

    No Known Activations