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

    Neuronpedia

    INDEX
    Explanations

    expressions related to social interactions and leisure activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parency
    -0.57
    省市镇
    -0.56
    orsese
    -0.55
     TestBed
    -0.53
    Nuorodos
    -0.52
     colline
    -0.52
    astie
    -0.51
     concret
    -0.51
     Kase
    -0.49
    lapsingToolbar
    -0.49
    POSITIVE LOGITS
     hang
    1.28
     Hang
    1.26
     HANG
    1.21
     hung
    1.16
     hanging
    1.14
     hangs
    1.08
    Hang
    1.08
    Hanging
    1.07
     Hanging
    1.06
    hanging
    1.05
    Act Density 0.054%

    No Known Activations