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

    Neuronpedia

    INDEX
    Explanations

    conjunctions indicating a transition or addition between sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "And."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.75
    houses
    -0.70
    scene
    -0.65
    ãģĨ
    -0.63
     ABE
    -0.63
    fell
    -0.63
    heads
    -0.62
    BILITIES
    -0.62
    PF
    -0.61
    cloth
    -0.61
    POSITIVE LOGITS
    romeda
    1.41
    rea
    1.24
    hra
    1.14
    alus
    1.08
    ersen
    0.92
    rew
    0.91
     secondly
    0.90
    rogens
    0.85
     furthermore
    0.84
    uin
    0.82
    Act Density 0.067%

    No Known Activations