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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the verb "do" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.81
    IntoConstraints
    -0.80
     Efq
    -0.77
     ſever
    -0.75
    latego
    -0.74
     poffible
    -0.74
    Portail
    -0.73
    Fordítás
    -0.72
     purpoſe
    -0.71
     neceff
    -0.69
    POSITIVE LOGITS
     do
    2.65
     doing
    2.58
    Doing
    2.37
     Doing
    2.31
    doing
    2.21
    do
    2.21
     Do
    2.17
    Do
    2.12
     done
    2.01
     DOING
    1.99
    Act Density 0.158%

    No Known Activations