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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases indicating strong agreement or support

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong agreement or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Welsh
    -0.75
    BALL
    -0.71
     Dynamics
    -0.71
     Romans
    -0.69
     Holmes
    -0.68
     Ballard
    -0.60
     Jobs
    -0.60
     Masters
    -0.58
     Icelandic
    -0.58
     Abyss
    -0.58
    POSITIVE LOGITS
    ourced
    1.22
    olute
    1.19
    pec
    1.18
    ounding
    1.16
    olver
    1.16
    umption
    1.14
    olutely
    1.10
    ound
    1.08
    ourcing
    1.08
    pell
    1.07
    Act Density 0.010%

    No Known Activations