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

    Neuronpedia

    INDEX
    Explanations

    references to environmental or health-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Calvo
    -0.83
     foglal
    -0.76
     poffe
    -0.68
     riuscito
    -0.66
    nsf
    -0.65
     Integrity
    -0.65
    пта
    -0.64
    5
    -0.64
    T
    -0.63
     capri
    -0.63
    POSITIVE LOGITS
    toward
    1.69
     toward
    1.63
     Toward
    1.63
    Toward
    1.56
    towards
    1.51
     Towards
    1.50
    Towards
    1.49
     towards
    1.42
     TOW
    1.10
     hacia
    1.10
    Act Density 0.062%

    No Known Activations