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

    Neuronpedia

    INDEX
    Explanations

    actions related to exploration and travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    timeofday
    -0.15
    loo
    -0.14
    vard
    -0.14
    elda
    -0.14
    pty
    -0.14
    ebek
    -0.14
    ocs
    -0.14
    creen
    -0.14
    elim
    -0.14
    .metamodel
    -0.14
    POSITIVE LOGITS
     trip
    0.29
     trips
    0.27
     visit
    0.24
     missions
    0.22
     mission
    0.21
     visits
    0.20
    trip
    0.20
     expedition
    0.19
     exped
    0.18
    _visit
    0.17
    Act Density 0.158%

    No Known Activations