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

    Neuronpedia

    INDEX
    Explanations

    words related to institutions, especially those starting with "Inst" and followed by other characters

    oai_token-act-pair · gpt-3.5-turbo

    references to institutional aspects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tone
    -0.74
    glers
    -0.72
    berries
    -0.70
    tsky
    -0.67
    neck
    -0.65
    dress
    -0.65
     basement
    -0.64
    RANT
    -0.63
    VEL
    -0.62
     sides
    -0.62
    POSITIVE LOGITS
    itutional
    1.25
     Inst
    1.21
    Inst
    1.18
    alled
    1.00
    inct
    0.96
    itution
    0.94
    itute
    0.92
    ellation
    0.91
     INST
    0.86
    inst
    0.84
    Act Density 0.005%

    No Known Activations