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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression towards goals and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unos
    -0.15
    prise
    -0.15
    ymax
    -0.15
    _startup
    -0.14
    ieu
    -0.14
    urger
    -0.14
    panse
    -0.14
    оÑģÑĤаÑĤ
    -0.13
    ott
    -0.13
     intervention
    -0.13
    POSITIVE LOGITS
     towards
    0.50
     toward
    0.48
    Towards
    0.45
     Towards
    0.44
     Tow
    0.33
     closer
    0.33
    åIJij
    0.29
    owards
    0.29
    oward
    0.28
     hacia
    0.28
    Act Density 0.138%

    No Known Activations