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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding logic and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubb
    -0.18
    .tf
    -0.15
    elper
    -0.14
    tent
    -0.14
    hq
    -0.14
     Bound
    -0.14
     jenter
    -0.14
     Jenner
    -0.14
    £½
    -0.14
    emento
    -0.13
    POSITIVE LOGITS
     appeal
    0.35
     Appeal
    0.34
     appeals
    0.32
     fall
    0.31
     Appeals
    0.29
     appealed
    0.26
     Fall
    0.25
     Logical
    0.24
     logical
    0.24
    Fall
    0.24
    Act Density 0.036%

    No Known Activations