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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or summation about past actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otas
    -0.16
     arriving
    -0.15
    .userInteractionEnabled
    -0.14
    å¡«
    -0.14
    CHASE
    -0.13
    essler
    -0.13
     accumulating
    -0.13
     succeeding
    -0.13
    enser
    -0.13
     proving
    -0.13
    POSITIVE LOGITS
     move
    0.59
     moved
    0.52
     Move
    0.51
    move
    0.50
     moving
    0.49
     moves
    0.49
    Move
    0.49
    -move
    0.47
    .move
    0.45
     MOVE
    0.44
    Act Density 0.048%

    No Known Activations