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

    Neuronpedia

    INDEX
    Explanations

    descriptors of emotional or environmental negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pand
    -0.16
    ighton
    -0.15
    letal
    -0.15
    .sponge
    -0.15
     McCorm
    -0.15
    illow
    -0.14
    .Extension
    -0.14
    ä¼į
    -0.14
    umbling
    -0.13
    λλη
    -0.13
    POSITIVE LOGITS
    lund
    0.17
    /cgi
    0.16
    ()."
    0.15
    fffffff
    0.15
     Scots
    0.14
     Bundy
    0.14
    rlen
    0.14
     конкÑĥÑĢ
    0.14
     nederland
    0.14
     localVar
    0.14
    Act Density 0.022%

    No Known Activations