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

    Neuronpedia

    INDEX
    Explanations

    website URLs and possibly related metadata

    oai_token-act-pair · gpt-3.5-turbo

    web-related content and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mood
    -0.49
    EStream
    -0.44
     Hubble
    -0.42
     puff
    -0.42
     behavi
    -0.41
    schild
    -0.40
    etheless
    -0.40
     SCP
    -0.39
     psychological
    -0.39
     oral
    -0.39
    POSITIVE LOGITS
    \-
    0.51
    ा
    0.50
    Ü
    0.49
    antes
    0.48
    aci
    0.47
    iott
    0.47
    endi
    0.46
    unda
    0.44
    γ
    0.44
    \\\\\\\\\\\\\\\\
    0.43
    Act Density 4.243%

    No Known Activations