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

    Neuronpedia

    INDEX
    Explanations

    directional phrases indicating movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Calvo
    -0.65
    isis
    -0.64
    T
    -0.63
     fatica
    -0.62
     Ig
    -0.61
     pep
    -0.61
    S
    -0.60
    pí
    -0.60
     MIC
    -0.59
    5
    -0.58
    POSITIVE LOGITS
    towards
    3.13
     towards
    3.12
     toward
    3.06
    toward
    3.00
     Towards
    2.98
    Towards
    2.88
     Toward
    2.85
    Toward
    2.55
     hacia
    2.11
     envers
    1.83
    Act Density 0.025%

    No Known Activations