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

    Neuronpedia

    INDEX
    Explanations

    the word "post" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "post" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grimm
    -0.63
     Huang
    -0.61
     drinks
    -0.60
    iencies
    -0.60
     Lucy
    -0.59
     friendly
    -0.59
    rity
    -0.59
     solid
    -0.58
     hardened
    -0.57
     Chao
    -0.56
    POSITIVE LOGITS
    post
    4.36
    posts
    2.86
    Post
    2.38
    POST
    2.11
     Post
    2.00
     post
    1.99
     POST
    1.75
    posted
    1.69
     posts
    1.36
    blog
    1.20
    Act Density 0.013%

    No Known Activations