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

    Neuronpedia

    INDEX
    Explanations

    prepositions and certain linking words indicating connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    which or whom after prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSlice
    -0.88
    Хьажоргаш
    -0.87
    DispatchToProps
    -0.76
    InitVars
    -0.76
    onedDateTime
    -0.73
    uxxxx
    -0.70
    SerializedSize
    -0.69
    참고
    -0.69
    EntityFramework
    -0.69
     useStyles
    -0.68
    POSITIVE LOGITS
     whom
    0.97
     wh
    0.81
     WH
    0.74
    wh
    0.69
     whi
    0.66
    whi
    0.63
    WH
    0.61
     whome
    0.59
     Whom
    0.58
     đó
    0.56
    Act Density 0.100%

    No Known Activations