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

    Neuronpedia

    INDEX
    Explanations

    phrases describing conditions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inium
    -0.18
    voy
    -0.17
    relation
    -0.17
     relation
    -0.15
     combination
    -0.15
    .connection
    -0.15
    sla
    -0.15
     Relation
    -0.14
     addition
    -0.14
    ston
    -0.14
    POSITIVE LOGITS
     front
    0.41
    front
    0.35
    -front
    0.31
     FRONT
    0.31
    _front
    0.26
     Front
    0.26
    Front
    0.25
     fronts
    0.24
     fron
    0.23
     frente
    0.21
    Act Density 0.247%

    No Known Activations