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

    Neuronpedia

    INDEX
    Explanations

    references to pipelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ille
    -0.15
    ILLE
    -0.14
    alez
    -0.14
    unga
    -0.14
    irc
    -0.14
    iel
    -0.14
    aldi
    -0.14
    leet
    -0.13
    rien
    -0.13
    lah
    -0.13
    POSITIVE LOGITS
     pil
    0.39
     Pil
    0.36
    grim
    0.24
    oting
    0.24
    oted
    0.22
    beam
    0.21
     pilgr
    0.21
     PIL
    0.20
     pilot
    0.19
    atus
    0.19
    Act Density 0.009%

    No Known Activations