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

    Neuronpedia

    INDEX
    Explanations

    expressions related to intentions and decisions about staying or continuing a course of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    ÑĪин
    -0.16
    ange
    -0.15
     comp
    -0.15
     Barton
    -0.15
    neh
    -0.15
    burgh
    -0.14
     priorities
    -0.14
     mar
    -0.14
    gil
    -0.14
    POSITIVE LOGITS
     permanent
    0.17
    aternity
    0.16
    Permanent
    0.16
     Permanent
    0.15
     tilt
    0.15
    366
    0.15
    permanent
    0.15
    425
    0.14
    ORA
    0.14
     permanently
    0.14
    Act Density 0.226%

    No Known Activations