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

    Neuronpedia

    INDEX
    Explanations

    sentence structures in the form "verb + subject + rest of sentence"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "did" and its variations, focusing on actions performed in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARN
    -0.65
    cipled
    -0.64
     WWF
    -0.62
    Topics
    -0.62
     Stra
    -0.60
    bent
    -0.60
     Autob
    -0.59
     Det
    -0.58
     Iss
    -0.58
    theless
    -0.57
    POSITIVE LOGITS
    pez
    1.05
    oms
    0.85
    zed
    0.80
    berman
    0.75
    adian
    0.74
    ggy
    0.73
    onga
    0.73
    lege
    0.70
    zing
    0.70
    omsday
    0.69
    Act Density 0.058%

    No Known Activations