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

    Neuronpedia

    INDEX
    Explanations

    people's names and locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal experiences or memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nominating
    -0.75
     nominees
    -0.75
     appointing
    -0.74
     discredited
    -0.74
    idelines
    -0.70
     nominations
    -0.69
     Presidential
    -0.66
     collusion
    -0.66
    afort
    -0.66
     favorable
    -0.65
    POSITIVE LOGITS
    é¾
    0.89
    veland
    0.81
     homeowner
    0.73
    Dispatch
    0.72
     Cree
    0.72
     Labrador
    0.71
     grandmother
    0.70
     Ezek
    0.70
     granddaughter
    0.69
     grandson
    0.68
    Act Density 0.721%

    No Known Activations