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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zek
    -0.15
    μά
    -0.14
     Erd
    -0.14
    herited
    -0.14
    ersen
    -0.14
     McCart
    -0.14
    ucken
    -0.14
    acio
    -0.13
    anim
    -0.13
    adel
    -0.13
    POSITIVE LOGITS
    ipo
    0.20
    ead
    0.16
     Orig
    0.15
    imp
    0.14
    fix
    0.13
    vp
    0.13
    enda
    0.13
    /***************************************************************************↵
    0.13
     VP
    0.13
    poi
    0.13
    Act Density 0.018%

    No Known Activations