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

    Neuronpedia

    INDEX
    Explanations

    references to the word "tree" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMB
    -0.17
    ieg
    -0.16
    midd
    -0.16
    ambia
    -0.15
    ersen
    -0.15
    irst
    -0.15
    opis
    -0.15
    omers
    -0.14
    sgi
    -0.14
    opi
    -0.14
    POSITIVE LOGITS
    acher
    0.26
    asured
    0.26
    asury
    0.24
    foil
    0.24
     tre
    0.24
    acle
    0.23
    asures
    0.23
    buch
    0.21
     Tre
    0.21
    asure
    0.20
    Act Density 0.008%

    No Known Activations