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

    Neuronpedia

    INDEX
    Explanations

    multiple variations of the word "way," indicating a focus on methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sq
    -0.18
    enthal
    -0.17
    aversable
    -0.16
    suz
    -0.16
    iks
    -0.16
    adders
    -0.15
    leo
    -0.15
    ulse
    -0.15
     widely
    -0.15
    sel
    -0.15
    POSITIVE LOGITS
    ward
    0.48
    finding
    0.31
    WARD
    0.26
    yyyy
    0.25
    yyy
    0.24
    far
    0.24
     forward
    0.24
    lay
    0.22
     thức
    0.21
    forward
    0.21
    Act Density 0.098%

    No Known Activations