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

    Neuronpedia

    INDEX
    Explanations

    references to individuals speaking or being mentioned in a conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.74
     pinulongan
    -0.74
     الرياضيه
    -0.71
    حياته
    -0.62
     محفوظة
    -0.59
    onAttach
    -0.57
    Erreferentziak
    -0.56
    Према
    -0.54
     chi̍t
    -0.53
     esternos
    -0.53
    POSITIVE LOGITS
    béco
    0.56
    кисло
    0.55
     giggled
    0.55
     said
    0.54
     Unmarshal
    0.52
     joked
    0.52
    brtc
    0.51
     shouted
    0.51
     replied
    0.51
     screamed
    0.51
    Act Density 0.049%

    No Known Activations