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

    Neuronpedia

    INDEX
    Explanations

    phrases related to absence of evidence or wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence of evidence or proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anders
    -0.81
    aunts
    -0.78
    gypt
    -0.77
    amph
    -0.72
    sembly
    -0.72
    É
    -0.71
    byss
    -0.70
    often
    -0.70
     Streets
    -0.69
    chin
    -0.69
    POSITIVE LOGITS
     wrongdoing
    1.45
     malice
    1.32
     motive
    1.25
     basis
    1.25
     collusion
    1.24
     connection
    1.23
     culp
    1.22
     violation
    1.22
     nexus
    1.20
     rationale
    1.20
    Act Density 0.209%

    No Known Activations