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

    Neuronpedia

    INDEX
    Explanations

    references to specific films or entertainment titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢĮâĢĮ
    -0.19
    Å¡ov
    -0.15
    yz
    -0.15
    theValue
    -0.15
    ething
    -0.14
    _DETECT
    -0.14
    veis
    -0.14
     Apost
    -0.14
    phetamine
    -0.14
    yth
    -0.14
    POSITIVE LOGITS
    oton
    0.21
    anggan
    0.21
     Pel
    0.20
    argon
    0.20
    agic
    0.19
    ican
    0.19
    icans
    0.18
    ÃŃcul
    0.18
    isser
    0.18
    leted
    0.17
    Act Density 0.007%

    No Known Activations