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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "seems" and its variations, indicating uncertainty or subjective opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.63
    istic
    -0.60
    ism
    -0.54
    memberof
    -0.49
    actus
    -0.49
     &
    -0.48
    menuStrip
    -0.48
    enter
    -0.44
    vare
    -0.44
    haway
    -0.44
    POSITIVE LOGITS
     like
    0.89
     unlikely
    0.83
     destined
    0.77
    ingly
    0.73
    Seems
    0.70
    lessly
    0.69
     likely
    0.69
    AndroidJUnit
    0.68
     awfully
    0.67
    tableFuture
    0.66
    Act Density 0.077%

    No Known Activations