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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "free" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    c
    -0.18
    soever
    -0.17
    jing
    -0.17
    ardi
    -0.16
    tra
    -0.16
    lej
    -0.15
    cle
    -0.15
    re
    -0.15
    faq
    -0.15
    so
    -0.15
    POSITIVE LOGITS
    bies
    0.26
    bie
    0.24
    /free
    0.18
    bsd
    0.17
    edom
    0.17
    haps
    0.16
    holm
    0.15
    endl
    0.15
    -ÑĤаки
    0.15
    -floating
    0.15
    Act Density 0.052%

    No Known Activations