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

    Neuronpedia

    INDEX
    Explanations

    words containing the substring "h" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the letter "h"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.85
    ãĥ¯
    -0.78
    bilt
    -0.69
    éĹĺ
    -0.69
    fman
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.65
    ãĥ´ãĤ¡
    -0.64
     Beware
    -0.64
     Clause
    -0.63
    EStream
    -0.63
    POSITIVE LOGITS
    oused
    1.38
    ousing
    1.24
    ulk
    1.21
    acking
    1.20
    anging
    1.19
    idd
    1.18
    ospital
    1.17
    olly
    1.16
    awk
    1.15
    anky
    1.15
    Act Density 0.022%

    No Known Activations