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

    Neuronpedia

    INDEX
    Explanations

    mentions of something starting with the letter 'H' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "H" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.78
     Beware
    -0.72
    enhagen
    -0.71
     CPR
    -0.68
     Conquest
    -0.66
    EStream
    -0.66
    lihood
    -0.65
     Chocobo
    -0.65
     totality
    -0.62
    terday
    -0.62
    POSITIVE LOGITS
    umble
    1.17
    anging
    1.17
    ospital
    1.16
    IGH
    1.13
    acking
    1.11
    awk
    1.10
    arsh
    1.10
    OST
    1.09
    AB
    1.09
    aim
    1.08
    Act Density 0.047%

    No Known Activations