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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to engagement and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.19
    someone
    -0.17
    hevik
    -0.16
    solver
    -0.16
    ëĿ¼ëıĦ
    -0.16
    apg
    -0.15
     Its
    -0.15
    oenix
    -0.15
    lico
    -0.14
    sprites
    -0.14
    POSITIVE LOGITS
    (ed
    0.63
    ings
    0.52
    ingly
    0.50
    led
    0.49
    eds
    0.49
    ned
    0.48
    ied
    0.47
    able
    0.45
    ed
    0.45
    ers
    0.44
    Act Density 0.276%

    No Known Activations