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

    Neuronpedia

    INDEX
    Explanations

    the various forms of the verb "make" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndPassword
    -0.16
    actics
    -0.15
    ients
    -0.15
    ncia
    -0.14
    enment
    -0.14
    иÑģÑģ
    -0.14
    격
    -0.14
    ivec
    -0.14
     veto
    -0.13
    wyn
    -0.13
    POSITIVE LOGITS
     sure
    0.39
     sense
    0.33
    leine
    0.31
     mistakes
    0.28
     decisions
    0.27
     progress
    0.27
     headlines
    0.25
     adjustments
    0.24
     noise
    0.24
     strides
    0.24
    Act Density 0.332%

    No Known Activations