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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or initiatives being taken

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "make" and its variations, indicating a focus on actions or processes of creation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.74
    Below
    -0.63
    hood
    -0.63
    CLOSE
    -0.63
     Niet
    -0.62
    swick
    -0.60
    rina
    -0.60
    ander
    -0.60
    ;;;;
    -0.59
    anders
    -0.59
    POSITIVE LOGITS
     sure
    1.55
     sense
    0.94
    hift
    0.92
     adjustments
    0.90
     Sure
    0.84
     Sense
    0.81
     ends
    0.77
     matters
    0.76
    sure
    0.74
     decisions
    0.74
    Act Density 0.113%

    No Known Activations