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

    Neuronpedia

    INDEX
    Explanations

    verbal phrases indicating ownership or entitlement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "claim" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arrang
    -0.80
     srf
    -0.78
     destro
    -0.74
    hitting
    -0.70
    committee
    -0.69
     wrench
    -0.67
     skew
    -0.65
     electing
    -0.64
     handshake
    -0.63
    jer
    -0.63
    POSITIVE LOGITS
    ulent
    0.85
    oux
    0.84
    aran
    0.82
    ifiable
    0.81
    oit
    0.76
    ulence
    0.74
    ignty
    0.74
    ril
    0.72
    ieu
    0.71
    ensional
    0.71
    Act Density 0.026%

    No Known Activations