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

    Neuronpedia

    INDEX
    Explanations

    instances of congratulations or expressions of achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MBER
    -0.18
    apyrus
    -0.17
    ansi
    -0.17
    Directories
    -0.15
    arkin
    -0.15
    adows
    -0.15
    indow
    -0.14
    bourg
    -0.14
     Gott
    -0.14
    anova
    -0.14
    POSITIVE LOGITS
    regation
    0.40
    rats
    0.38
    estion
    0.36
    rat
    0.31
    reg
    0.30
    ested
    0.29
    ole
    0.26
    lom
    0.26
    reve
    0.25
    reso
    0.24
    Act Density 0.010%

    No Known Activations