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

    Neuronpedia

    INDEX
    Explanations

    expressions related to negative sentiments and frustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.65
     mnoho
    -0.63
     infine
    -0.55
    OIR
    -0.55
    роль
    -0.54
    fromString
    -0.50
     algemeen
    -0.49
     nasional
    -0.49
    rsen
    -0.48
     sahiptir
    -0.47
    POSITIVE LOGITS
     dudes
    1.30
     stuff
    1.20
     outta
    1.18
     dude
    1.13
     guys
    1.08
     thingy
    1.07
     gotta
    1.06
     fellas
    1.02
     folks
    1.02
     fella
    1.02
    Act Density 0.523%

    No Known Activations