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

    Neuronpedia

    INDEX
    Explanations

    words related to influence and impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to influence and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ft
    -0.69
    ithing
    -0.61
    iphate
    -0.61
    rentices
    -0.60
    Tan
    -0.59
    puted
    -0.59
    tri
    -0.58
    algia
    -0.58
    clamation
    -0.58
    sw
    -0.58
    POSITIVE LOGITS
     shaping
    0.94
     adversely
    0.83
     materially
    0.82
     perceptions
    0.81
     negatively
    0.81
     impacts
    0.77
     impacting
    0.75
     havoc
    0.72
     influencing
    0.71
     advis
    0.69
    Act Density 0.071%

    No Known Activations