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

    Neuronpedia

    INDEX
    Explanations

    assertions and beliefs about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.84
     Houſe
    -0.82
     Anſ
    -0.70
     itſelf
    -0.69
    Tikang
    -0.69
     pleaſure
    -0.69
     témoig
    -0.69
     ſta
    -0.68
     يتيمه
    -0.67
     ſont
    -0.67
    POSITIVE LOGITS
     believes
    0.60
     believe
    0.51
     считает
    0.46
     felt
    0.46
     Felt
    0.45
     считают
    0.41
    setVerticalGroup
    0.41
     believed
    0.40
     think
    0.39
    Felt
    0.38
    Act Density 0.549%

    No Known Activations