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

    Neuronpedia

    INDEX
    Explanations

    phrases related to repetition or doing something again

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetition or the concept of repeating itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bridge
    -0.72
    roy
    -0.66
    istant
    -0.65
     Shed
    -0.63
    ctuary
    -0.60
     Sponsor
    -0.60
    awei
    -0.59
     Angelo
    -0.58
     Clement
    -0.58
     Mesa
    -0.57
    POSITIVE LOGITS
     mantra
    0.92
     playbook
    0.91
     phrase
    0.81
     phrases
    0.80
     same
    0.77
     footsteps
    0.75
     clich
    0.74
    dayName
    0.74
     oft
    0.69
     tropes
    0.69
    Act Density 0.226%

    No Known Activations