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

    Neuronpedia

    INDEX
    Explanations

    repeated usage of the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omin
    -0.16
    .Companion
    -0.15
    sci
    -0.14
    ubar
    -0.14
     Kak
    -0.14
    hta
    -0.14
    ardo
    -0.13
    esture
    -0.13
    SSF
    -0.13
    oman
    -0.13
    POSITIVE LOGITS
    ãĤ±ãĥĥãĥĪ
    0.15
    åĦĢ
    0.15
    .Modules
    0.14
     tol
    0.13
    pio
    0.13
    att
    0.13
    ỡ
    0.13
    upp
    0.13
    lund
    0.13
    lei
    0.13
    Act Density 0.040%

    No Known Activations